INDEX

Explanations

phrases related to disclaimers and legal notices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

æĪ

-0.14

orse

-0.14

sta

-0.13

sel

-0.13

_IOC

-0.13

cer

-0.13

 Mits

-0.13

 post

-0.13

POSITIVE LOGITS

oux

0.15

atty

0.15

rik

0.15

oad

0.15

ague

0.15

coni

0.15

ritz

0.14

Ð¼ÐµÑĪ

0.14

ctica

0.14

ÚĨØ§Ø±

0.14

Activations Density 0.008%

phrases related to disclaimers and legal notices

No Comments

No Known Activations

phrases related to disclaimers and legal notices

No Comments

No Known Activations