INDEX

Explanations

terms related to health, safety, and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

otu

-0.17

 Complete

-0.15

Complete

-0.15

bei

-0.15

 complete

-0.14

.complete

-0.14

ãģ¨ãģĵãĤį

-0.14

alg

-0.14

complete

-0.14

POSITIVE LOGITS

aupt

0.16

Ã¦r

0.15

undler

0.15

rossover

0.15

åĤ

0.15

udeau

0.15

aepernick

0.15

áº¡

0.14

ä¿Ŀ

0.14

plorer

0.14

Activations Density 0.004%

terms related to health, safety, and governance

No Comments

No Known Activations