INDEX

Explanations

references to programming and code-related concepts

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

loff

-0.17

QualifiedName

-0.16

-0.15

abr

-0.15

gba

-0.15

afone

-0.15

-0.14

otes

-0.14

loh

-0.13

Ð»Ð¸Ð²Ñĸ

-0.13

POSITIVE LOGITS

 onto

0.25

 into

0.24

Into

0.22

_into

0.21

onto

0.21

 Into

0.20

into

0.19

 vÃło

0.17

aser

0.16

.Std

0.15

Activations Density 0.363%

references to programming and code-related concepts

No Comments

No Known Activations