INDEX

Explanations

expressions of choice and individual discretion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

uzzi

-0.18

izzy

-0.14

itious

-0.14

shed

-0.14

egral

-0.14

Ä±cÄ±

-0.13

iphy

-0.13

datal

-0.13

EEK

-0.13

bourg

-0.13

POSITIVE LOGITS

 discretion

0.39

 subjective

0.35

 personal

0.33

 choice

0.30

 decision

0.28

 judgment

0.28

 preference

0.28

 opinion

0.27

 individual

0.26

personal

0.26

Activations Density 0.193%

expressions of choice and individual discretion

No Comments

No Known Activations