INDEX

Explanations

instances of numerical information and related phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

aviest

-0.17

yx

-0.15

elage

-0.15

 ÏĢÎ¬Î½Ïī

-0.15

ichen

-0.14

å¼ķãģį

-0.14

="__

-0.14

Ãªn

-0.14

ixel

-0.13

-transitional

-0.13

POSITIVE LOGITS

 some

0.61

some

0.50

 Some

0.48

Some

0.44

 SOME

0.42

ä¸ĢäºĽ

0.41

.some

0.40

 einige

0.39

_some

0.36

 Ð½ÐµÐºÐ¾ÑĤÐ¾ÑĢÑĭÐµ

0.35

Activations Density 0.149%

instances of numerical information and related phrases

No Comments

No Known Activations