INDEX

Explanations

mentions of different pronouns, particularly those referring to people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

antz

-0.16

vided

-0.15

urt

-0.14

rais

-0.14

reira

-0.14

oksen

-0.14

 Sharp

-0.14

ungs

-0.14

Î¯Î±

-0.13

llum

-0.13

POSITIVE LOGITS

«a

0.15

eth

0.14

CriticalSection

0.14

Ã¼re

0.14

 Richards

0.13

éģĬ

0.13

ufen

0.13

 herr

0.13

 Affero

0.13

QUIT

0.13

Activations Density 0.034%

mentions of different pronouns, particularly those referring to people

No Comments

No Known Activations