INDEX

Explanations

dates and numerical values in a chronological context

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

ography

-0.15

ä¸»ä¹ī

-0.15

kud

-0.14

oined

-0.14

åĿĽ

-0.14

ISTA

-0.14

Î¹Î¬

-0.13

.scalablytyped

-0.13

Gram

-0.13

OGRAPH

-0.13

POSITIVE LOGITS

assa

0.16

ruk

0.15

antas

0.15

cce

0.15

unta

0.14

´

0.14

uya

0.14

USIC

0.14

 Advocate

0.14

bang

0.14

Activations Density 0.016%

dates and numerical values in a chronological context

No Comments

No Known Activations