INDEX

Explanations

proper nouns, specifically names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

stoff

-0.15

berman

-0.15

ibly

-0.15

ainer

-0.15

TEGR

-0.14

cribed

-0.14

tps

-0.14

vard

-0.14

cors

-0.14

Mud

-0.13

POSITIVE LOGITS

.micro

0.17

aded

0.16

errat

0.16

illo

0.14

onio

0.14

 æĻ

0.14

zam

0.14

\modules

0.14

 êµ

0.14

venta

0.14

Activations Density 0.200%

proper nouns, specifically names and titles

No Comments

No Known Activations