INDEX

Explanations

occurrences of the word "Bo" and its variants

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

Ã©gor

-0.16

manda

-0.15

ãĥ³ãĥĦ

-0.15

ure

-0.14

Enums

-0.14

ter

-0.14

rollo

-0.14

ì§ĳ

-0.14

à¸´à¸ļ

-0.14

 opak

-0.14

POSITIVE LOGITS

Bo

0.22

bo

0.21

oleans

0.21

oby

0.20

levard

0.20

Bo

0.19

ogie

0.19

omer

0.19

eing

0.18

ehr

0.18

Activations Density 0.014%

occurrences of the word "Bo" and its variants

No Comments

No Known Activations