INDEX

Explanations

references to publication and media dissemination

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

 surfaces

-0.15

oney

-0.15

-0.14

erton

-0.14

isser

-0.14

last

-0.14

emann

-0.14

 bere

-0.14

POSITIVE LOGITS

Ã¼st

0.16

afone

0.16

anford

0.15

ADDE

0.15

tember

0.15

_mD

0.15

_mC

0.15

ä¹¾

0.14

UILayout

0.14

SplitOptions

0.14

Activations Density 0.157%

references to publication and media dissemination

No Comments

No Known Activations