INDEX

Explanations

legal terminology and references to court proceedings

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

acos

-0.15

 unanim

-0.15

ÐĶÐĲ

-0.14

NotExist

-0.14

ÄŁiz

-0.13

_None

-0.13

Moy

-0.13

/compiler

-0.13

illos

-0.13

isphere

-0.13

POSITIVE LOGITS

esa

0.15

AMA

0.15

Ð¾Ð»ÐµÐ²Ð°

0.14

ebek

0.14

tero

0.14

.fd

0.14

auss

0.14

 supper

0.13

 Hund

0.13

olet

0.13

Activations Density 0.063%

legal terminology and references to court proceedings

No Comments

No Known Activations