INDEX

Explanations

references to individuals and their notable works or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ordon

-0.15

aeper

-0.14

icken

-0.14

å¯¿

-0.14

putation

-0.14

 nonexistent

-0.14

erti

-0.14

 Techn

-0.13

 editions

-0.13

byterian

-0.13

POSITIVE LOGITS

 martin

0.19

 MART

0.18

 Martin

0.15

Martin

0.15

ìĭĿ

0.14

Ã½val

0.14

/***/

0.14

-Mart

0.14

 mart

0.14

 Mart

0.14

Activations Density 0.024%

references to individuals and their notable works or activities

No Comments

No Known Activations