INDEX

Explanations

actions or behaviors involving acting or behaving in specific ways

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

IDEO

-0.18

combe

-0.17

quipment

-0.15

assage

-0.15

ache

-0.15

cade

-0.15

adies

-0.14

esktop

-0.14

allee

-0.14

POSITIVE LOGITS

uate

0.24

 upon

0.19

inch

0.17

uator

0.16

ively

0.16

 decis

0.16

 atas

0.16

/react

0.15

acts

0.15

onor

0.15

Activations Density 0.022%

actions or behaviors involving acting or behaving in specific ways

No Comments

No Known Activations