INDEX

Explanations

various forms of the word "race" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

shire

-0.19

aires

-0.16

anguages

-0.16

-0.15

-HT

-0.15

ately

-0.15

ency

-0.15

self

-0.15

sh

-0.15

ness

-0.15

POSITIVE LOGITS

horse

0.19

erp

0.16

TokenType

0.16

/umd

0.16

presso

0.16

LAN

0.15

course

0.14

ovnÃŃ

0.14

dirty

0.14

ourcem

0.14

Activations Density 0.028%

various forms of the word "race" and related terms

No Comments

No Known Activations