INDEX

Explanations

references to timelines or temporal markers indicating the past or present

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Apprec

-0.14

 Weeks

-0.14

irsch

-0.14

INET

-0.14

 swim

-0.14

 Supply

-0.14

 Ã©c

-0.13

Rug

-0.13

corp

-0.13

Eck

-0.13

POSITIVE LOGITS

 year

0.24

 Ð³Ð¾Ð´Ñĥ

0.20

year

0.18

.year

0.17

eon

0.16

pta

0.16

 ÑĢÐ¾ÐºÑĥ

0.16

 jaar

0.15

 mole

0.15

 Jahr

0.15

Activations Density 0.044%

references to timelines or temporal markers indicating the past or present

No Comments

No Known Activations