INDEX

Explanations

web addresses and sources of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

olk

-0.19

olia

-0.17

 Magazine

-0.16

 magazine

-0.16

 Editor

-0.15

 Newspaper

-0.15

-0.14

illo

-0.14

Pap

-0.14

 Column

-0.14

POSITIVE LOGITS

actionDate

0.16

âĢĮØ³ÛĮ

0.14

Occurrences

0.14

etur

0.14

Trait

0.13

tick

0.13

Fcn

0.13

ogue

0.13

ableObject

0.13

Kaw

0.13

Activations Density 0.098%

web addresses and sources of information

No Comments

No Known Activations