INDEX

Explanations

the word "our" and its variants, as well as related possessive pronouns and references to community or group ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

angkan

-0.17

igger

-0.16

ISCO

-0.16

Ð°ÑĤÐµÐ³

-0.15

aked

-0.14

tility

-0.14

NaN

-0.14

è·¡

-0.14

rogate

-0.14

iais

-0.14

POSITIVE LOGITS

 Noon

0.14

ese

0.14

 Ð§Ð°Ñģ

0.14

YSTEM

0.14

frey

0.14

adro

0.14

naire

0.13

 thirst

0.13

amo

0.13

ard

0.13

Activations Density 0.104%

the word "our" and its variants, as well as related possessive pronouns and references to community or group ownership

No Comments

No Known Activations