INDEX

Explanations

fragments and elements in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

'icon

-0.19

itto

-0.16

 initialValue

-0.16

yg

-0.15

kud

-0.15

zell

-0.15

muh

-0.14

oundary

-0.14

sticks

-0.14

RLF

-0.14

POSITIVE LOGITS

Abr

0.14

Kw

0.14

SON

0.14

icia

0.13

 disc

0.13

asting

0.13

IfExists

0.13

 lasting

0.13

bris

0.13

OrCreate

0.13

Activations Density 0.148%

fragments and elements in a programming context

No Comments

No Known Activations