INDEX

Explanations

instances of the letter 'a' in different contexts

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

acus

-0.15

assen

-0.14

alion

-0.14

å·»

-0.14

à¸£

-0.14

 Hale

-0.14

cÃŃ

-0.14

ventions

-0.13

autÃ©

-0.13

çħ

-0.13

POSITIVE LOGITS

oret

0.18

ount

0.16

imary

0.15

à¸¸à¸į

0.14

itta

0.14

arend

0.14

ieee

0.14

atre

0.14

Activations Density 0.024%

instances of the letter 'a' in different contexts

No Comments

No Known Activations