INDEX

Explanations

discussions surrounding political decisions and changes in government policy

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

Ø®ÛĮ

-0.14

illard

-0.14

çŃĴ

-0.14

Ø±ÙĪØ´

-0.13

unwrap

-0.13

urer

-0.13

ersistent

-0.13

ekler

-0.13

idunt

-0.13

bilt

-0.13

POSITIVE LOGITS

 backtrack

0.38

 reversed

0.34

 retract

0.32

 reversal

0.32

 cave

0.32

 reversing

0.31

 relent

0.30

 reconsider

0.30

 capit

0.30

 reverse

0.30

Activations Density 0.171%

discussions surrounding political decisions and changes in government policy

No Comments

No Known Activations