INDEX

Explanations

references to specific programming or technical components and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

landers

-0.17

 Bund

-0.15

asa

-0.14

edy

-0.14

avir

-0.14

pole

-0.14

STONE

-0.14

 trab

-0.14

Tun

-0.14

aland

-0.14

POSITIVE LOGITS

gies

0.16

gÄ±

0.16

unch

0.15

ëŁ¬

0.15

uger

0.15

_locale

0.15

uzzer

0.14

.Debugger

0.14

igram

0.14

opak

0.14

Activations Density 0.004%

references to specific programming or technical components and systems

No Comments

No Known Activations