INDEX

Explanations

references to cultural and social structures or norms

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

ussy

-0.15

erosis

-0.14

-the

-0.14

ITS

-0.14

oz

-0.14

ieten

-0.14

 TypeInfo

-0.14

 Gott

-0.14

))-

-0.14

peg

-0.13

POSITIVE LOGITS

—to

0.20

—for

0.19

—in

0.17

—that

0.17

--

0.16

§

0.15

toy

0.15

-than

0.15

,on

0.15

—as

0.15

Activations Density 0.038%

references to cultural and social structures or norms

No Comments

No Known Activations