INDEX

Explanations

phrases that involve the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÌĨ

-0.20

aliz

-0.15

 Misc

-0.15

Ãºc

-0.15

}elseif

-0.14

iker

-0.14

leftright

-0.14

Ð´Ð°ÑĤ

-0.14

lea

-0.14

uren

-0.14

POSITIVE LOGITS

ools

0.17

 ç³

0.16

 Erick

0.15

imoto

0.15

opia

0.15

OfWork

0.14

-of

0.14

Gig

0.14

tt

0.14

 Crop

0.14

Activations Density 0.029%

phrases that involve the word "of."

No Comments

No Known Activations