INDEX

Explanations

themes of neutrality and balance in discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Bounding

-0.17

 âĨĵ

-0.16

rete

-0.15

shortcut

-0.14

coni

-0.14

iena

-0.14

tail

-0.14

ottage

-0.14

oard

-0.14

mise

-0.14

POSITIVE LOGITS

 neutral

0.55

 neutrality

0.54

 Neutral

0.51

neutral

0.49

-neutral

0.47

Neutral

0.46

 impartial

0.41

 neutr

0.34

 neither

0.28

 balanced

0.28

Activations Density 0.197%

themes of neutrality and balance in discourse

No Comments

No Known Activations