INDEX

Explanations

phrases related to law, governance, and regulatory compliance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

rez

-0.18

åĲ¦

-0.16

 conce

-0.14

reject

-0.14

çīĩ

-0.13

ordo

-0.13

Å¯Å¾

-0.13

 pres

-0.13

imity

-0.13

éĻĲ

-0.13

POSITIVE LOGITS

 voluntary

0.18

 indu

0.16

 instead

0.16

nud

0.16

anela

0.16

 rather

0.15

 subt

0.15

æŀļ

0.15

 gentle

0.15

nici

0.15

Activations Density 0.213%

phrases related to law, governance, and regulatory compliance

No Comments

No Known Activations