INDEX

Explanations

references to films and documentaries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Gap

-0.15

onto

-0.15

TM

-0.14

aday

-0.14

luv

-0.14

áº¥u

-0.13

_TOO

-0.13

zap

-0.13

æĿ¿

-0.13

ADIO

-0.13

POSITIVE LOGITS

ajas

0.15

ruk

0.15

atica

0.15

 commodo

0.14

mercial

0.14

apro

0.14

itchens

0.14

fat

0.13

$?

0.13

Ã¦r

0.13

Activations Density 0.377%

references to films and documentaries

No Comments

No Known Activations