INDEX

Explanations

references to specific educational or social projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

erez

-0.13

 simplest

-0.13

 useClass

-0.12

ÅĻeba

-0.12

Å¡ka

-0.12

odzi

-0.12

oves

-0.11

 poprvÃ©

-0.11

yna

-0.11

 sobie

-0.11

POSITIVE LOGITS

 other

1.14

other

0.90

åħ¶ä»ĸ

0.84

 autres

0.78

 OTHER

0.76

 Other

0.75

 andere

0.75

-other

0.74

Other

0.74

 otros

0.74

Activations Density 1.007%

references to specific educational or social projects

No Comments

No Known Activations