INDEX

Explanations

references to specific locations or contexts within a legal document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 norms

-0.15

lates

-0.15

amment

-0.14

 norm

-0.14

ekt

-0.13

tat

-0.13

 damned

-0.13

ypi

-0.13

[top

-0.13

agrant

-0.13

POSITIVE LOGITS

psilon

0.16

Äįi

0.14

 ÐĿÐ°Ð¹

0.13

iture

0.13

ignum

0.13

abler

0.13

erk

0.13

 Bison

0.13

urette

0.13

eldon

0.13

Activations Density 0.756%

references to specific locations or contexts within a legal document

No Comments

No Known Activations