INDEX

Explanations

phrases and statements indicating stress and chaotic situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

monds

-0.14

acus

-0.14

uder

-0.14

ndo

-0.13

Ã³j

-0.13

entric

-0.13

eyin

-0.13

 æ¿

-0.12

bic

-0.12

obic

-0.12

POSITIVE LOGITS

add

0.69

Add

0.64

add

0.57

Add

0.54

 added

0.53

-add

0.52

 adds

0.51

 Added

0.51

.add

0.50

_add

0.49

Activations Density 0.312%

phrases and statements indicating stress and chaotic situations

No Comments

No Known Activations