INDEX

Explanations

terms related to zippers and zip codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

éľŀ

-0.16

ughter

-0.15

pill

-0.15

uish

-0.15

agements

-0.15

lv

-0.14

 clipboard

-0.14

ices

-0.14

abbage

-0.14

POSITIVE LOGITS

pered

0.37

per

0.25

pering

0.21

zap

0.20

fel

0.19

 sobie

0.19

/post

0.18

perm

0.17

izo

0.17

arton

0.17

Activations Density 0.006%

terms related to zippers and zip codes

No Comments

No Known Activations