INDEX

Explanations

references to academic citations and publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

apper

-0.18

IAS

-0.17

roe

-0.15

jal

-0.15

_CI

-0.15

atel

-0.15

æ®Ĭ

-0.14

 Tiles

-0.14

ãĤĩ

-0.14

FACE

-0.14

POSITIVE LOGITS

StdString

0.19

icina

0.16

Ric

0.15

ystate

0.15

ric

0.15

ydk

0.14

UserController

0.14

ÃŃcul

0.14

ych

0.14

 timed

0.14

Activations Density 0.025%

references to academic citations and publication details

No Comments

No Known Activations