INDEX

Explanations

words related to specific identifiers or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

itler

-0.17

Æ°Æ¡ng

-0.15

ares

-0.15

ENCHMARK

-0.15

ÐłÐĿ

-0.15

asser

-0.15

Æ¯

-0.15

à¥įà¤·à¤ķ

-0.14

ickle

-0.14

POSITIVE LOGITS

ÑģÑı

0.21

oten

0.16

éĸĵ

0.16

ly

0.15

 themselves

0.15

se

0.14

ÑĤÐµÑģÑĮ

0.14

me

0.14

PHA

0.14

Activations Density 0.083%

words related to specific identifiers or titles

No Comments

No Known Activations