INDEX

Explanations

concepts related to ideas, theories, and explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ivre

-0.16

ivec

-0.15

 Woodward

-0.14

iya

-0.14

loh

-0.14

inand

-0.14

-Sah

-0.14

 VÅ¡ech

-0.14

ontent

-0.13

elt

-0.13

POSITIVE LOGITS

as

0.41

how

0.41

 regarding

0.31

how

0.30

 about

0.28

 what

0.26

 cÃ³mo

0.26

 ÐºÐ°Ðº

0.24

 vá»ģ

0.23

 whether

0.23

Activations Density 0.298%

concepts related to ideas, theories, and explanations

No Comments

No Known Activations

concepts related to ideas, theories, and explanations

No Comments

No Known Activations