INDEX

Explanations

mentions of the letter "O"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

erty

-0.16

 Kore

-0.15

 Rolling

-0.14

agate

-0.14

tract

-0.14

immune

-0.14

mÃ©na

-0.14

-0.13

opsis

-0.13

reative

-0.13

POSITIVE LOGITS

cala

0.22

conto

0.22

ahu

0.22

conom

0.21

.pen

0.21

steen

0.21

villa

0.20

ubre

0.20

 Fallon

0.20

xn

0.20

Activations Density 0.018%

mentions of the letter "O"

No Comments

No Known Activations