INDEX

Explanations

comparisons and contrasts in opinions or descriptions

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

 vulgar

-0.15

 rude

-0.14

theid

-0.14

 bold

-0.14

 adrenaline

-0.14

agger

-0.14

çĭĤ

-0.14

 lively

-0.14

 Independence

-0.14

Ã»t

-0.14

POSITIVE LOGITS

 gent

0.45

 gentle

0.44

 soft

0.42

soft

0.38

gent

0.38

 softer

0.36

Soft

0.36

 Soft

0.35

 peaceful

0.34

 quiet

0.32

Activations Density 0.578%

comparisons and contrasts in opinions or descriptions

No Comments

No Known Activations