INDEX

Explanations

references to a production crew or team 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

cz

-0.16

esium

-0.15

tdown

-0.15

hausen

-0.14

bourne

-0.14

ãĥ³ãĤ¸

-0.14

 Milo

-0.14

steen

-0.14

ritz

-0.14

UBE

-0.14

POSITIVE LOGITS

members

0.48

member

0.41

 members

0.40

 member

0.34

mates

0.32

-member

0.31

-members

0.31

 Members

0.29

Members

0.29

_member

0.28

Activations Density 0.026%

references to a production crew or team in various contexts

No Comments

No Known Activations