INDEX

Explanations

instances of the word "number" and its context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

egers

-0.23

ients

-0.16

inges

-0.16

eners

-0.16

inki

-0.15

ÄįnÃŃk

-0.15

alls

-0.15

iggins

-0.15

clusions

-0.15

criptions

-0.15

POSITIVE LOGITS

 dozen

0.18

 number

0.16

ero

0.16

 ÑĩÐ¸

0.16

 factors

0.15

 different

0.15

eo

0.15

load

0.15

ator

0.15

 amount

0.15

Activations Density 0.060%

instances of the word "number" and its context

No Comments

No Known Activations