INDEX

Explanations

references to specific data repositories and scientific project identifiers

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

-0.15

 unintention

-0.15

erais

-0.15

atz

-0.14

veh

-0.14

uchar

-0.14

 theories

-0.14

lech

-0.14

unr

-0.14

astes

-0.13

POSITIVE LOGITS

psz

0.17

ëĭ´

0.15

RELATED

0.15

zcze

0.14

reon

0.14

 ASIC

0.13

stay

0.13

elop

0.13

taÅŁ

0.13

.pitch

0.13

Activations Density 0.045%

references to specific data repositories and scientific project identifiers

No Comments

No Known Activations