INDEX

Explanations

references to royalty or kings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Kraj

-0.16

deki

-0.16

omor

-0.15

Ú¯Ø§Ùĩ

-0.15

abr

-0.14

okit

-0.14

 nÄĥ

-0.14

ullah

-0.14

gether

-0.14

Ú©ÙĨ

-0.14

POSITIVE LOGITS

pin

0.29

pins

0.23

ston

0.20

eton

0.19

ergarten

0.18

horn

0.16

holm

0.16

lets

0.16

 Animalia

0.15

roups

0.15

Activations Density 0.028%

references to royalty or kings in various contexts

No Comments

No Known Activations