INDEX

Explanations

references to swimming and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

.scalablytyped

-0.16

getDisplay

-0.16

xdb

-0.15

phis

-0.15

çī©

-0.15

phans

-0.15

uges

-0.15

ocio

-0.15

eniable

-0.14

ament

-0.14

POSITIVE LOGITS

 Swimming

0.21

 swimming

0.21

/sw

0.20

mer

0.20

 swim

0.18

 Swim

0.17

rat

0.15

posium

0.15

wear

0.15

irc

0.15

Activations Density 0.010%

references to swimming and related activities

No Comments

No Known Activations