INDEX

Explanations

instances of the word "at"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.30

ur

-0.29

er

-0.29

acl

-0.28

es

-0.28

oS

-0.27

aub

-0.26

tur

-0.26

ar

-0.25

POSITIVE LOGITS

tempts

0.18

tractive

0.17

rices

0.17

ernal

0.17

tribution

0.17

ellite

0.16

rans

0.16

las

0.16

tract

0.16

ric

0.16

Activations Density 0.037%

instances of the word "at"

No Comments

No Known Activations