INDEX

Explanations

phrases related to cultural identity and heritage

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

Ã¤nder

-0.15

feld

-0.15

áº£m

-0.15

_rg

-0.14

ÑĢÐ¾ÑĤ

-0.14

portrait

-0.14

Ã¼st

-0.14

alue

-0.14

wig

-0.14

etik

-0.14

POSITIVE LOGITS

 means

0.24

 direct

0.20

 sheer

0.19

use

0.18

 various

0.18

/by

0.18

ought

0.18

puts

0.17

 participation

0.16

 continued

0.16

Activations Density 0.096%

phrases related to cultural identity and heritage

No Comments

No Known Activations