INDEX

Explanations

instances of the word "at"

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

 Lobby

-0.17

ãģ¾ãģ¾

-0.16

nee

-0.15

ÙĪÙħÛĮ

-0.15

ittal

-0.15

han

-0.14

 remainder

-0.14

ses

-0.14

ponder

-0.14

etto

-0.14

POSITIVE LOGITS

 least

0.79

 Least

0.65

least

0.64

Least

0.60

_least

0.53

 menos

0.49

 less

0.47

 moins

0.45

 LESS

0.37

 Less

0.36

Activations Density 0.067%

instances of the word "at"

No Comments

No Known Activations