INDEX

Explanations

instances of the abbreviation "st" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

tee

-0.17

arine

-0.15

malÄ±

-0.15

mou

-0.15

ç¯

-0.15

rn

-0.14

ARGE

-0.14

LEE

-0.14

ictures

-0.14

 Este

-0.14

POSITIVE LOGITS

Ã¤ll

0.30

ora

0.28

yr

0.27

Ã¶r

0.27

ift

0.26

Ã¤l

0.26

Ã¥

0.26

ads

0.25

Ã¤m

0.24

Ã¤ng

0.24

Activations Density 0.005%

instances of the abbreviation "st" and its variations

No Comments

No Known Activations