INDEX

Explanations

references to Jewish identity 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

als

-0.16

kers

-0.16

ker

-0.15

 Islam

-0.15

ument

-0.15

ative

-0.15

urs

-0.15

ode

-0.15

 Pett

-0.14

isi

-0.14

POSITIVE LOGITS

-Owned

0.19

enco

0.18

-Christian

0.18

uales

0.16

ness

0.16

/non

0.15

anken

0.15

ÃŃky

0.14

otionEvent

0.14

ABCDEFGHIJKLMNOP

0.14

Activations Density 0.029%

references to Jewish identity and related terms

No Comments

No Known Activations