INDEX

Explanations

conditional phrases indicating potential outcomes or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 belie

-0.15

recht

-0.15

Î¼Î¿ÏĤ

-0.14

 Watts

-0.13

ssi

-0.13

pth

-0.13

pill

-0.13

pollo

-0.13

emma

-0.13

aken

-0.13

POSITIVE LOGITS

brane

0.16

æ¡ĳ

0.16

0.15

ê³¼ìĿĺ

0.15

ÑģÑĮ

0.14

 Crud

0.14

á¹

0.14

Inspectable

0.14

eniz

0.14

0.13

Activations Density 0.056%

conditional phrases indicating potential outcomes or consequences

No Comments

No Known Activations