INDEX

Explanations

references to the color "brown" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.15

iom

-0.15

gle

-0.15

ermint

-0.15

aec

-0.15

uem

-0.15

hev

-0.14

obao

-0.14

chal

-0.14

uen

-0.14

POSITIVE LOGITS

lee

0.33

rig

0.32

sville

0.31

stein

0.26

ells

0.25

lie

0.25

LEE

0.25

stone

0.24

low

0.24

ell

0.23

Activations Density 0.012%

references to the color "brown" and its variations in different contexts

No Comments

No Known Activations