INDEX

Explanations

references to space and capacity for various subjects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Thames

-0.17

Å¡tÃŃ

-0.16

assertCount

-0.16

imler

-0.16

 ########.

-0.15

ForObject

-0.15

benh

-0.14

 ÑģÑĥÑĤ

-0.14

uish

-0.14

è±Ĭ

-0.14

POSITIVE LOGITS

agle

0.14

voke

0.14

¼åĲĪ

0.14

kol

0.14

pir

0.14

OLER

0.14

Ñİ

0.14

 Lind

0.14

egal

0.13

Activations Density 0.023%

references to space and capacity for various subjects or concepts

No Comments

No Known Activations