INDEX

Explanations

phrases related to something being very large or significant

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.15

acades

-0.14

bie

-0.14

se

-0.14

semb

-0.14

 gris

-0.14

Æ°á»£t

-0.14

-dess

-0.13

INTR

-0.13

zek

-0.13

POSITIVE LOGITS

stakes

0.20

-scale

0.17

wich

0.16

ilio

0.15

 amounts

0.15

amount

0.14

sword

0.14

azo

0.14

Knife

0.14

mary

0.14

Activations Density 0.042%

phrases related to something being very large or significant

No Comments

No Known Activations