INDEX

Explanations

instances of significant community or collective concepts and responsibilities within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Lair

-0.14

klady

-0.14

ĺħ

-0.13

ÏĦÎ¿Î»

-0.13

otch

-0.13

ÙħØ¨Ø±

-0.13

 Barker

-0.12

Tay

-0.12

 cock

-0.12

toMatch

-0.12

POSITIVE LOGITS

PU

0.51

PU

0.48

pu

0.47

pu

0.47

Pu

0.46

Pu

0.46

BU

0.44

bu

0.43

hu

0.43

 Puerto

0.43

Activations Density 0.724%

instances of significant community or collective concepts and responsibilities within a narrative context

No Comments

No Known Activations