INDEX

Explanations

phrases related to writing and document creation

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

onis

-0.18

llen

-0.18

isphere

-0.15

isÃŃ

-0.15

ocos

-0.14

etus

-0.14

erule

-0.14

shit

-0.13

phant

-0.13

REAM

-0.13

POSITIVE LOGITS

 restart

0.20

 Inch

0.17

ieu

0.16

 bure

0.15

 reun

0.15

 alist

0.15

ymax

0.15

 clinic

0.15

Erg

0.15

erg

0.15

Activations Density 0.011%

phrases related to writing and document creation

No Comments

No Known Activations