INDEX

Explanations

URLs and references related to news stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Fork

-0.16

 forks

-0.15

:"-"`↵

-0.15

mÃ©na

-0.14

etal

-0.14

[++

-0.14

bard

-0.14

ena

-0.14

iel

-0.14

POSITIVE LOGITS

embros

0.16

 haar

0.16

Ð°Ñģ

0.16

led

0.15

uge

0.15

 Ashley

0.14

#ad

0.14

ç½²

0.14

Fab

0.14

Ree

0.14

Activations Density 0.005%

URLs and references related to news stories

No Comments

No Known Activations

URLs and references related to news stories

No Comments

No Known Activations