INDEX

Explanations

expressions of perception or belief in social dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 direct

-0.14

ernel

-0.14

 Ø¬ÙĦ

-0.14

 pari

-0.14

 Primitive

-0.13

 unrelated

-0.13

irect

-0.13

ooth

-0.13

Äįet

-0.13

POSITIVE LOGITS

 undecided

0.47

amb

0.42

 uncertainty

0.40

 ambiguity

0.39

 neutral

0.39

 ambiguous

0.38

 inde

0.38

 uncertain

0.38

 unsure

0.37

ambiguous

0.36

Activations Density 0.376%

expressions of perception or belief in social dynamics

No Comments

No Known Activations