INDEX

Explanations

instances of the word "new" related to programming or object creation

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

-0.15

Ã©t

-0.15

ele

-0.14

HK

-0.14

bara

-0.14

TRANS

-0.14

/OR

-0.14

ado

-0.14

å»³

-0.14

POSITIVE LOGITS

 Farrell

0.14

à¹Ģà¸ģà¸Ńà¸£

0.14

says

0.14

uggy

0.14

 bypass

0.14

osto

0.13

IGH

0.13

ieee

0.13

oons

0.13

Activations Density 0.010%

instances of the word "new" related to programming or object creation

No Comments

No Known Activations