INDEX

Explanations

phrases indicating the occurrence or announcement of events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iets

-0.16

ensen

-0.15

ayer

-0.15

ritch

-0.14

\Active

-0.13

.nextSibling

-0.13

cg

-0.13

jmu

-0.13

 thereafter

-0.13

POSITIVE LOGITS

 follows

0.28

 heels

0.27

 follow

0.23

hot

0.22

follow

0.20

 heals

0.20

hot

0.20

Follow

0.18

 heel

0.18

 FOLLOW

0.18

Activations Density 0.020%

phrases indicating the occurrence or announcement of events or situations

No Comments

No Known Activations