INDEX

Explanations

instances of the word "too."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

mp

-0.19

pu

-0.19

 nÃło

-0.18

ry

-0.18

ron

-0.17

st

-0.16

ford

-0.16

wood

-0.16

 toch

-0.16

-0.15

POSITIVE LOGITS

led

0.26

ledo

0.24

gether

0.24

/from

0.20

thers

0.19

0.18

kest

0.17

oooooooo

0.17

xygen

0.16

pez

0.16

Activations Density 0.037%

instances of the word "too."

No Comments

No Known Activations