INDEX

Explanations

indicators of legal or formal writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oman

-0.16

Ø®ÙĪØ§ÙĨ

-0.15

coni

-0.15

orian

-0.14

 filmer

-0.14

ioni

-0.14

 ÑģÐ¿ÑĢÐ°Ð²

-0.14

ApiResponse

-0.14

 Ð¾ÑĢÐ³Ð°Ð½Ð¸

-0.14

uni

-0.14

POSITIVE LOGITS

ispens

0.15

 NavParams

0.15

hte

0.15

achine

0.14

aqu

0.14

andler

0.14

 DISCLAIMER

0.14

gne

0.14

acht

0.14

 Variation

0.14

Activations Density 0.001%

indicators of legal or formal writing

No Comments

No Known Activations