INDEX

Explanations

references to demos or trial versions of software or games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

se

-0.16

ä¹İ

-0.16

iff

-0.15

istine

-0.15

Ã¡bb

-0.14

orm

-0.14

æĮģãģ¡

-0.14

à¸ģà¸³

-0.14

cie

-0.14

POSITIVE LOGITS

strate

0.21

stration

0.18

linger

0.16

Ø®ÛĮ

0.16

Ã¼t

0.15

abay

0.15

TRS

0.15

/demo

0.15

onse

0.14

Activations Density 0.007%

references to demos or trial versions of software or games

No Comments

No Known Activations