INDEX

Explanations

legal terminology and references related to court proceedings and legal documentation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

pth

-0.17

inski

-0.15

acios

-0.15

ÏĨÎ±

-0.15

 Tobias

-0.14

 upper

-0.14

ç½®

-0.14

umble

-0.13

ltra

-0.13

cx

-0.13

POSITIVE LOGITS

ennon

0.15

qus

0.15

nung

0.15

acket

0.14

 Synd

0.14

ãĤ®

0.14

vais

0.13

åħ¸

0.13

/command

0.13

 templ

0.13

Activations Density 0.126%

legal terminology and references related to court proceedings and legal documentation

No Comments

No Known Activations