INDEX

Explanations

words related to various professions and social roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uye

-0.17

jiang

-0.15

ÅĤa

-0.14

rang

-0.14

abal

-0.14

ulet

-0.14

was

-0.14

ÏĦÎŃ

-0.14

ighton

-0.13

 BÃł

-0.13

POSITIVE LOGITS

 often

0.23

 generally

0.23

often

0.19

 Generally

0.17

 souvent

0.17

 typically

0.17

 usually

0.16

Often

0.16

 Often

0.16

 notoriously

0.15

Activations Density 0.173%

words related to various professions and social roles

No Comments

No Known Activations