INDEX

Explanations

references to academic authors and their works

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

.bunifuFlatButton

-0.16

stalk

-0.15

utos

-0.15

erness

-0.15

oman

-0.14

ynos

-0.14

adÃŃ

-0.14

/company

-0.14

orsi

-0.14

ocab

-0.14

POSITIVE LOGITS

argon

0.15

et

0.15

 ìĶ

0.14

NullException

0.13

 Blank

0.13

 imag

0.13

[&

0.13

geÃ§

0.13

ade

0.13

ìĬ¬

0.13

Activations Density 0.100%

references to academic authors and their works

No Comments

No Known Activations