INDEX

Explanations

phrases relating to personal responsibility and self-reflection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

stad

-0.15

 cope

-0.15

also

-0.14

rus

-0.14

 sometimes

-0.14

umd

-0.14

sometimes

-0.14

 rather

-0.14

è£ħ

-0.13

ISTA

-0.13

POSITIVE LOGITS

 cÃłng

0.15

ALIGN

0.15

ĵ¨

0.15

ÏĦÏį

0.15

adel

0.15

 succeeds

0.15

Ø²Ø±

0.15

 cannot

0.15

jez

0.14

Repeated

0.14

Activations Density 0.167%

phrases relating to personal responsibility and self-reflection

No Comments

No Known Activations