INDEX

Explanations

terms related to legal institutions and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

unar

-0.16

din

-0.15

reff

-0.15

dic

-0.15

arella

-0.14

haf

-0.14

sled

-0.14

izoph

-0.14

nak

-0.14

urable

-0.14

POSITIVE LOGITS

ovky

0.15

 Stam

0.15

 Mile

0.14

SSI

0.14

ãĥĥãĥĪ

0.14

 Rush

0.14

orian

0.13

 Ferguson

0.13

DU

0.13

Î½Î¿Ïį

0.13

Activations Density 0.617%

terms related to legal institutions and their activities

No Comments

No Known Activations