INDEX

Explanations

queries or questions related to user interface behavior

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

jerne

-0.16

 Burk

-0.15

vÃ©

-0.15

appa

-0.14

olen

-0.14

äº¤æµģ

-0.14

 ancestral

-0.14

xab

-0.14

 olsun

-0.14

apa

-0.14

POSITIVE LOGITS

×ķ×

0.28

×

0.27

×ª

0.25

×

0.25

×ĳ

0.24

 ×ĳ

0.23

×ŀ

0.23

 Aviv

0.23

 ×©

0.23

 ×Ķ

0.22

Activations Density 0.025%

queries or questions related to user interface behavior

No Comments

No Known Activations