INDEX

Explanations

the word "well."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

wap

-0.14

itag

-0.14

upported

-0.14

ycastle

-0.14

elsen

-0.14

 Doub

-0.14

ailles

-0.14

quette

-0.14

'gc

-0.13

holes

-0.13

POSITIVE LOGITS

-active

0.15

iros

0.15

 ÏĦÏģÎ¿

0.14

LI

0.13

tz

0.13

icie

0.13

ursos

0.13

.boost

0.13

 Huck

0.13

ague

0.13

Activations Density 0.025%

the word "well."

No Comments

No Known Activations