INDEX

Explanations

specific types of food or dishes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ensburg

-0.15

 zemÄĽ

-0.15

 dirig

-0.15

 æ©

-0.15

acz

-0.15

 khÃ³a

-0.15

rott

-0.14

ascade

-0.14

ëª°

-0.14

æĿŁ

-0.14

POSITIVE LOGITS

XO

0.17

 gore

0.17

 glut

0.17

ABC

0.17

çµ

0.17

ud

0.16

mee

0.16

 Clay

0.16

 peanuts

0.16

 pand

0.15

Activations Density 0.072%

specific types of food or dishes

No Comments

No Known Activations