INDEX

Explanations

mentions of the name "Kim."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

iffin

-0.18

 Millet

-0.17

ful

-0.16

GIN

-0.16

oplan

-0.15

mann

-0.15

sing

-0.15

-0.14

ucci

-0.14

 reservations

-0.14

POSITIVE LOGITS

med

0.16

éĢģæĸĻçĦ¡æĸĻ

0.15

ung

0.15

 adulti

0.14

rray

0.14

.desktop

0.14

hlas

0.14

ãģ£ãģ¨

0.14

uetype

0.14

Ã¡ze

0.13

Activations Density 0.010%

mentions of the name "Kim."

No Comments

No Known Activations