INDEX

Explanations

terms related to software and technical 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

ollo

-0.16

_ISO

-0.15

uto

-0.14

ardo

-0.14

_tar

-0.14

edback

-0.14

ajs

-0.14

indre

-0.14

NDAR

-0.14

Squared

-0.14

POSITIVE LOGITS

.shtml

0.16

 Silver

0.15

DialogContent

0.14

Auf

0.14

dehyde

0.14

'{{

0.14

Deg

0.13

house

0.13

ates

0.13

ozÃŃ

0.13

Activations Density 0.005%

terms related to software and technical concepts

No Comments

No Known Activations