INDEX

Explanations

references to museums and museum-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Coordinate

-0.15

á»ĭnh

-0.14

Ã½Å¡

-0.14

ongan

-0.14

arious

-0.13

ioned

-0.13

cq

-0.13

 ëĦ¤ìĿ´íĬ¸

-0.13

å¾ĭ

-0.13

á»įng

-0.13

POSITIVE LOGITS

 Fine

0.19

 history

0.19

 fine

0.19

nict

0.17

Fine

0.16

 contemporary

0.16

 History

0.16

 Natural

0.16

fine

0.16

 natural

0.16

Activations Density 0.020%

references to museums and museum-related content

No Comments

No Known Activations