INDEX

Explanations

instances of dialogue and conversational elements

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

ÑĢÐµÑģ

-0.14

affen

-0.14

ãĥ¼ãĥģ

-0.14

ãĥ³ãĥĲãĥ¼

-0.13

mÃŃt

-0.13

Ø§ÙĩÙħ

-0.13

zp

-0.13

ergarten

-0.13

ackson

-0.13

POSITIVE LOGITS

 notice

0.43

 noticing

0.40

 notices

0.39

 noticed

0.39

noticed

0.35

 Notice

0.33

notice

0.32

 hear

0.30

Notice

0.30

see

0.29

Activations Density 0.317%

instances of dialogue and conversational elements

No Comments

No Known Activations