INDEX

Explanations

elements related to code and programming libraries

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

arro

-0.15

ÂŃn

-0.15

oling

-0.15

Ã©ric

-0.15

cla

-0.15

ra

-0.14

raquo

-0.14

-record

-0.14

ircuit

-0.13

 defence

-0.13

POSITIVE LOGITS

oreach

0.18

lech

0.16

eyim

0.15

isku

0.14

_streams

0.14

 Mein

0.13

 Trafford

0.13

rites

0.13

Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

0.13

 pedig

0.13

Activations Density 0.004%

elements related to code and programming libraries

No Comments

No Known Activations