INDEX

Explanations

references to technical specifications and installation instructions

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

Ð·Ñĭ

-0.15

gre

-0.14

_TE

-0.14

adm

-0.14

heit

-0.14

è§

-0.14

Ã¶m

-0.13

ÐµÐ¹Ð½

-0.13

GAN

-0.13

nul

-0.13

POSITIVE LOGITS

inel

0.15

 elektronik

0.14

UI

0.14

é§

0.14

afs

0.14

 Jarvis

0.13

 marshal

0.13

enna

0.13

ustr

0.13

 Marsh

0.13

Activations Density 0.190%

references to technical specifications and installation instructions

No Comments

No Known Activations