INDEX

Explanations

expressions of doubt or skepticism regarding assumptions or actions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

anela

-0.20

ulton

-0.17

 ç³

-0.15

rien

-0.14

«ĺ

-0.14

strar

-0.14

resden

-0.13

emax

-0.13

wd

-0.13

alse

-0.13

POSITIVE LOGITS

itag

0.16

aliz

0.16

utom

0.15

ãĥŁãĥ¥

0.14

erence

0.14

wel

0.14

 Carrier

0.14

angers

0.14

 naturally

0.13

ithe

0.13

Activations Density 0.017%

expressions of doubt or skepticism regarding assumptions or actions

No Known Activations