INDEX

Explanations

occurrences of the preposition "in."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 false

-0.15

PRESS

-0.14

ald

-0.14

marshall

-0.14

 Renders

-0.14

arrera

-0.14

imar

-0.14

ÄĽt

-0.14

URLRequest

-0.14

 soon

-0.13

POSITIVE LOGITS

à¹īà¸Ńà¸Ļ

0.14

âĹİ

0.14

oly

0.14

0.13

Ð·Ð´

0.13

Ont

0.13

 Wich

0.13

_NOP

0.13

 âĹİ

0.13

Unsafe

0.13

Activations Density 0.150%

occurrences of the preposition "in."

No Comments

No Known Activations