INDEX

Explanations

mentions of the term "cha."

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

ezi

-0.16

ils

-0.15

éĥİ

-0.15

itta

-0.15

aes

-0.14

ariat

-0.14

oxy

-0.14

emens

-0.14

inal

-0.14

POSITIVE LOGITS

Cha

0.29

Cha

0.27

cha

0.25

otic

0.21

uffer

0.19

cha

0.17

otes

0.17

ë¡Ģ

0.17

acters

0.17

 disorder

0.17

Activations Density 0.010%

mentions of the term "cha."

No Comments

No Known Activations