INDEX

Explanations

phrases related to identity or classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

-0.15

 Gardner

-0.15

Ä°ÅŁ

-0.14

SizeMode

-0.14

iesz

-0.14

uria

-0.13

Ð°Ð»ÑĮÐ½Ðµ

-0.13

ighthouse

-0.13

 McDonald

-0.13

aru

-0.13

POSITIVE LOGITS

consts

0.16

enthal

0.15

ypse

0.15

itty

0.14

andi

0.14

 hull

0.14

-mf

0.14

ÐµÐ²Ð¸Ñĩ

0.14

rance

0.13

Activations Density 0.064%

phrases related to identity or classification

No Comments

No Known Activations