INDEX

Explanations

punctuation marks and their frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anz

-0.15

abi

-0.15

 DropIndex

-0.15

ÙħØ§Ùħ

-0.14

nin

-0.14

 ÄĲÃ³

-0.14

dit

-0.14

autoload

-0.13

omi

-0.13

arez

-0.13

POSITIVE LOGITS

Os

0.27

Dur

0.25

Na

0.23

0.21

 Exist

0.21

Os

0.21

Em

0.21

Ap

0.20

Um

0.20

No

0.20

Activations Density 0.007%

punctuation marks and their frequency

No Comments

No Known Activations