INDEX

Explanations

terms related to anti-Semitism and its various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

omed

-0.16

aily

-0.15

fully

-0.15

umbled

-0.15

ÏĦÎ¬

-0.15

nad

-0.14

rosso

-0.14

omer

-0.14

rgan

-0.14

ogue

-0.13

POSITIVE LOGITS

EDIA

0.15

lesia

0.15

beck

0.15

ept

0.14

ofi

0.14

pter

0.14

 Brushes

0.14

Î¼Î¿Ïģ

0.14

loat

0.13

 Baker

0.13

Activations Density 0.002%

terms related to anti-Semitism and its various forms

No Comments

No Known Activations