INDEX

Explanations

queries or questions related to programming and technical issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 surely

-0.18

icious

-0.17

lush

-0.15

plu

-0.15

apas

-0.15

report

-0.14

 FOREIGN

-0.13

oste

-0.13

ap

-0.13

POSITIVE LOGITS

eyse

0.18

oves

0.16

StackNavigator

0.15

 tÃ¼k

0.14

utations

0.14

naires

0.14

elts

0.14

ecies

0.14

INLINE

0.14

 dart

0.14

Activations Density 0.016%

queries or questions related to programming and technical issues

No Comments

No Known Activations