INDEX

Explanations

terms related to anti-discrimination and historical legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.18

-0.15

hte

-0.15

å´

-0.15

åĢĴ

-0.15

anÃ¡

-0.15

/stretch

-0.14

ALSE

-0.14

anka

-0.14

odium

-0.14

POSITIVE LOGITS

isis

0.16

 seedu

0.15

ful

0.14

aminer

0.14

Äĩi

0.14

fully

0.14

 ä»·æł¼

0.14

reau

0.13

áº¹

0.13

 Antar

0.13

Activations Density 0.003%

terms related to anti-discrimination and historical legal contexts

No Comments

No Known Activations