INDEX

Explanations

the presence of the token "pl" 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

inite

-0.15

imitives

-0.14

å®®

-0.14

 é¢¨

-0.14

 Scaling

-0.14

anga

-0.14

echa

-0.14

 å®®

-0.14

hausen

-0.14

.dk

-0.14

POSITIVE LOGITS

oner

0.17

rÃ¡n

0.16

ourg

0.16

ihan

0.14

cheme

0.14

cheng

0.14

utsch

0.14

irsch

0.14

itr

0.14

egov

0.14

Activations Density 0.006%

the presence of the token "pl" in various contexts

No Comments

No Known Activations