INDEX

Explanations

geographic locations or regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mlin

-0.15

olta

-0.15

à¹Ģà¸¢

-0.15

ibar

-0.15

POCH

-0.15

è²¼

-0.15

agne

-0.15

çİĩ

-0.14

isko

-0.14

okit

-0.14

POSITIVE LOGITS

 region

0.17

Cog

0.15

 area

0.15

 Bell

0.15

 Punch

0.14

CHR

0.14

-region

0.14

ÙĪØ°

0.14

-area

0.14

Bell

0.14

Activations Density 0.052%

geographic locations or regions

No Comments

No Known Activations