INDEX

Explanations

connections between scientific findings and their implications or effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

nob

-0.15

Ã¼ss

-0.14

amburger

-0.14

 Lens

-0.13

åĪ»

-0.13

deg

-0.13

tha

-0.13

_already

-0.13

omu

-0.13

 lens

-0.13

POSITIVE LOGITS

 attributed

0.61

 attribute

0.59

attrib

0.56

 attrib

0.55

 atrib

0.55

 Attribute

0.53

attribute

0.52

 attributes

0.51

 attribution

0.50

 Attributes

0.47

Activations Density 0.166%

connections between scientific findings and their implications or effects

No Comments

No Known Activations