INDEX

Explanations

references to citations and figures in academic or research contexts

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

 territorial

-0.16

itchen

-0.15

edula

-0.15

 Morrow

-0.15

itory

-0.15

lander

-0.15

alsy

-0.15

 Experimental

-0.14

FormItem

-0.14

itore

-0.14

POSITIVE LOGITS

fid

0.20

 Ãĸzel

0.17

 Feast

0.17

 Astroph

0.17

.vaadin

0.17

pri

0.17

 molec

0.17

\Bundle

0.17

 discre

0.16

 turnover

0.16

Activations Density 0.023%

references to citations and figures in academic or research contexts

No Comments

No Known Activations