INDEX

Explanations

references to external sources or links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

cene

-0.17

 Singer

-0.16

ickness

-0.15

inem

-0.15

 æ¯

-0.15

rawn

-0.14

dk

-0.14

 Stokes

-0.14

aney

-0.13

aten

-0.13

POSITIVE LOGITS

 links

0.36

 Links

0.31

 link

0.29

_links

0.28

Links

0.26

 Link

0.25

-links

0.24

links

0.24

 External

0.24

_link

0.23

Activations Density 0.003%

references to external sources or links

No Comments

No Known Activations