INDEX

Explanations

instances of the word "по" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

baum

-0.15

uet

-0.15

maal

-0.15

Ģìŀ¥

-0.15

noon

-0.14

ÑĪÐµÐ²

-0.14

uspend

-0.14

AndView

-0.14

kou

-0.14

 å¨

-0.14

POSITIVE LOGITS

ese

0.17

ame

0.16

esses

0.16

pur

0.16

ahr

0.16

viz

0.15

jav

0.15

-the

0.15

 mutual

0.15

viz

0.14

Activations Density 0.009%

instances of the word "по" in different contexts

No Comments

No Known Activations