INDEX

Explanations

significant actions, interactions, and narratives within a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

affer

-0.17

owie

-0.17

enson

-0.15

 Separator

-0.14

itations

-0.14

ŃĶ

-0.14

ãģ¨ãģĨ

-0.13

bane

-0.13

ÐµÑĦ

-0.13

ewater

-0.13

POSITIVE LOGITS

 addAction

0.15

iner

0.15

uro

0.15

 xOffset

0.15

jer

0.14

ulumi

0.14

upply

0.14

ardown

0.14

icht

0.14

ãĥĥãĥĦ

0.14

Activations Density 0.022%

significant actions, interactions, and narratives within a variety of contexts

No Comments

No Known Activations