INDEX

Explanations

expressions of pride

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

zan

-0.18

agnar

-0.16

 adulti

-0.15

antar

-0.15

ivan

-0.15

 pÃ¡s

-0.15

cono

-0.14

 Commerce

-0.14

insky

-0.14

ileÅŁ

-0.14

POSITIVE LOGITS

asil

0.14

apus

0.14

lient

0.14

ÐµÐ½Ð½Ð¾

0.14

full

0.13

Ø±ÙĬÙĥ

0.13

sled

0.13

Ø§Ùī

0.13

ãĥĲãĥ¼

0.13

uous

0.13

Activations Density 0.006%

expressions of pride

No Comments

No Known Activations