INDEX

Explanations

terms related to cultural references and social commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

DataExchange

-0.15

 unpredictable

-0.13

 lá»ĳi

-0.13

 lively

-0.13

 playful

-0.13

longleftrightarrow

-0.13

UseProgram

-0.13

 patched

-0.13

 colorful

-0.12

 similar

-0.12

POSITIVE LOGITS

 bullshit

0.20

 shit

0.19

isms

0.18

fuck

0.18

 FAIL

0.17

BS

0.17

 clich

0.17

 cred

0.17

enn

0.17

Activations Density 0.183%

terms related to cultural references and social commentary

No Comments

No Known Activations