INDEX

Explanations

mentions of British nationality or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Areas

-0.19

.Areas

-0.18

ehr

-0.17

ÏīÎ´

-0.15

areas

-0.15

 åĸ

-0.15

ENU

-0.15

Areas

-0.15

eras

-0.15

declspec

-0.14

POSITIVE LOGITS

 wing

0.18

uegos

0.17

ilters

0.16

 intent

0.15

 Wing

0.14

wing

0.14

 Brock

0.14

wind

0.14

-American

0.14

oplay

0.14

Activations Density 0.047%

mentions of British nationality or related terms

No Comments

No Known Activations