INDEX

Explanations

occurrences of the word "an" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ingly

-0.15

 baÅŁÄ±na

-0.15

gaard

-0.15

insky

-0.15

 Davies

-0.14

etail

-0.14

antic

-0.14

auss

-0.14

 spreads

-0.14

kÃ¶

-0.13

POSITIVE LOGITS

ther

0.32

ointed

0.20

archy

0.20

iling

0.19

agrams

0.18

vil

0.17

thers

0.17

iline

0.17

ony

0.17

/the

0.17

Activations Density 0.247%

occurrences of the word "an" in various contexts

No Comments

No Known Activations