INDEX

Explanations

phrases indicating stress and time constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

entric

-0.15

uder

-0.14

Otherwise

-0.14

 otherwise

-0.14

monds

-0.13

otherwise

-0.13

 Otherwise

-0.13

RAD

-0.13

ZN

-0.13

Ã³j

-0.13

POSITIVE LOGITS

add

0.72

Add

0.65

add

0.57

 added

0.56

Add

0.56

-add

0.54

 adds

0.54

 Added

0.53

_add

0.52

.add

0.51

Activations Density 0.179%

phrases indicating stress and time constraints

No Comments

No Known Activations