INDEX

Explanations

references to cooking or culinary themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

icari

-0.15

ê°Ī

-0.14

_fb

-0.14

anker

-0.14

subclass

-0.14

 Late

-0.13

ENA

-0.13

 Painter

-0.13

ê±°ëŀĺê°Ģ

-0.13

immel

-0.13

POSITIVE LOGITS

upp

0.17

eph

0.16

Dt

0.15

te

0.15

 parc

0.15

uctor

0.14

tee

0.14

ogle

0.14

uw

0.14

Activations Density 0.009%

references to cooking or culinary themes

No Comments

No Known Activations