INDEX

Explanations

phrases related to legal and regulatory frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ekim

-0.15

akeup

-0.14

bery

-0.14

pee

-0.14

ache

-0.14

Ð°Ñİ

-0.14

ERGE

-0.14

ockey

-0.13

ë¡ľ

-0.13

sik

-0.13

POSITIVE LOGITS

ally

0.23

nement

0.23

als

0.20

 circumstances

0.19

 conditions

0.18

0.17

naires

0.17

 Conditions

0.16

nn

0.16

Activations Density 0.045%

phrases related to legal and regulatory frameworks

No Comments

No Known Activations