INDEX

Explanations

references to legal professionals and their statements in legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

lisi

-0.15

ut

-0.14

kees

-0.14

assets

-0.14

amble

-0.14

rew

-0.14

ASI

-0.14

elia

-0.14

animate

-0.13

TO

-0.13

POSITIVE LOGITS

aylight

0.19

:class

0.15

 Krish

0.15

 èĩªåĬ¨çĶŁæĪĲ

0.15

roje

0.14

.ALIGN

0.14

alarÄ±ndan

0.14

erokee

0.14

.generated

0.14

ChangeEvent

0.14

Activations Density 0.081%

references to legal professionals and their statements in legal contexts

No Comments

No Known Activations