INDEX

Explanations

mentions of the name "Thor."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ropoda

-0.17

zer

-0.16

archy

-0.15

Ø´ÛĮ

-0.15

gor

-0.14

 è©ķ

-0.14

Ø§Ø¦Ùħ

-0.14

erman

-0.14

ÑĤ

-0.14

ivre

-0.14

POSITIVE LOGITS

acic

0.32

nton

0.32

OUGH

0.24

arin

0.21

bj

0.20

wald

0.20

sten

0.19

 Thor

0.19

azine

0.18

stein

0.18

Activations Density 0.003%

mentions of the name "Thor."

No Comments

No Known Activations