INDEX

Explanations

references to rebuilding or rewriting processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

alted

-0.15

uther

-0.15

acs

-0.14

orf

-0.14

uter

-0.13

/layouts

-0.13

ACS

-0.13

jez

-0.13

ope

-0.13

och

-0.13

POSITIVE LOGITS

 entirely

0.18

rewrite

0.17

 altogether

0.16

itters

0.15

asket

0.15

 completely

0.15

filesize

0.15

 entire

0.15

\<^

0.15

Î¹Ïİ

0.14

Activations Density 0.101%

references to rebuilding or rewriting processes

No Comments

No Known Activations