INDEX

Explanations

mentions of the word "cool" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ynchronously

-0.20

eer

-0.18

idal

-0.18

ecure

-0.17

atically

-0.16

ecurity

-0.16

\API

-0.16

etc

-0.16

eter

-0.16

lene

-0.16

POSITIVE LOGITS

idge

0.32

ness

0.27

ers

0.26

 Britann

0.23

headed

0.23

ibri

0.23

IDGE

0.23

 breeze

0.23

ies

0.23

io

0.23

Activations Density 0.017%

mentions of the word "cool" and its variations

No Comments

No Known Activations