INDEX

Explanations

cooking-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ouv

-0.15

iva

-0.14

 Fare

-0.14

ãģĹãģĭ

-0.14

liv

-0.14

 boards

-0.14

 fork

-0.13

 Airways

-0.13

POSITIVE LOGITS

_Arg

0.16

uitka

0.15

omap

0.15

à¹īà¸²à¸¢

0.15

orman

0.14

unner

0.14

å®¤

0.14

kili

0.14

arrings

0.14

ieg

0.14

Activations Density 0.015%

cooking-related terms

No Comments

No Known Activations