INDEX

Explanations

references to food and food-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 phá»ĳ

-0.15

iner

-0.15

stÃ¥

-0.14

inz

-0.14

 whisk

-0.14

à¸§à¸¡

-0.14

eeper

-0.14

uid

-0.13

ilters

-0.13

antt

-0.13

POSITIVE LOGITS

stuff

0.20

erman

0.15

lice

0.14

 Nack

0.14

ermen

0.14

letters

0.14

arris

0.14

/feed

0.14

 Bakan

0.14

ogg

0.14

Activations Density 0.043%

references to food and food-related concepts

No Comments

No Known Activations