INDEX

Explanations

the word "there."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

eller

-0.15

ãĥ¼ãĥĨãĤ£

-0.15

lsen

-0.15

á»ĵ

-0.14

rÃ¡t

-0.14

eeper

-0.14

ayla

-0.14

ceed

-0.14

rlen

-0.14

stan

-0.14

POSITIVE LOGITS

inoa

0.17

udo

0.16

 Burns

0.15

0.14

ÃľM

0.14

ëĿ¼ëıĦ

0.13

yt

0.13

aset

0.13

Activations Density 0.009%

the word "there."

No Comments

No Known Activations