INDEX

Explanations

percentages and statistical data concerning opinions or responses

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pari

-0.14

Äįet

-0.14

ernel

-0.14

eda

-0.13

ih

-0.13

ĺħ

-0.13

 clums

-0.13

-dom

-0.13

_VISIBLE

-0.13

çµĦ

-0.13

POSITIVE LOGITS

 neutral

0.48

 undecided

0.46

 Neutral

0.45

amb

0.42

Neutral

0.42

neutral

0.41

 ambiguity

0.40

 uncertainty

0.40

 neutrality

0.39

 ambiguous

0.39

Activations Density 0.300%

percentages and statistical data concerning opinions or responses

No Comments

No Known Activations