INDEX

Explanations

references to programming instructions and usage examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

unar

-0.17

 Wilkinson

-0.16

ozo

-0.15

 Trafford

-0.15

ogenerated

-0.15

imeter

-0.15

QueryBuilder

-0.14

SCO

-0.14

_ulong

-0.14

SCO

-0.14

POSITIVE LOGITS

dek

0.15

rien

0.14

Pag

0.14

ackson

0.14

0.13

eah

0.13

 usage

0.13

 appearance

0.13

cade

0.13

Activations Density 0.047%

references to programming instructions and usage examples

No Comments

No Known Activations