INDEX

Explanations

components and identifiers related to programming, particularly in a web or software development context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Sortable

-0.19

outers

-0.16

Î½Îµ

-0.15

ombat

-0.14

icter

-0.14

ackers

-0.14

oire

-0.14

 heart

-0.14

Ð¸ÑĤÐµ

-0.13

esub

-0.13

POSITIVE LOGITS

gaard

0.17

0.15

ending

0.15

ir

0.15

occo

0.14

 Manit

0.14

oding

0.14

estic

0.14

sey

0.13

Activations Density 0.014%

components and identifiers related to programming, particularly in a web or software development context

No Comments

No Known Activations