INDEX

Explanations

references to families or groups of related items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

yer

-0.15

ila

-0.15

idia

-0.14

ocha

-0.14

izon

-0.14

ó

-0.14

.INSTANCE

-0.14

umed

-0.14

 Lobby

-0.14

ared

-0.13

POSITIVE LOGITS

eko

0.15

 nackte

0.15

odos

0.15

ppe

0.15

Ã²a

0.15

zcze

0.14

 series

0.14

avanaugh

0.14

Fre

0.13

Activations Density 0.087%

references to families or groups of related items or concepts

No Comments

No Known Activations