INDEX

Explanations

legal terminology and processes related to court cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lernen

-0.16

Thunk

-0.15

lint

-0.14

ourke

-0.14

attles

-0.14

 Apprent

-0.14

stinence

-0.14

onet

-0.14

ocard

-0.14

ITTE

-0.14

POSITIVE LOGITS

 cass

0.24

 Chamber

0.21

 chamber

0.18

 proceedings

0.18

 Cass

0.17

 Advocate

0.17

åºŃ

0.17

:init

0.16

 procedure

0.16

 suspect

0.16

Activations Density 0.067%

legal terminology and processes related to court cases

No Comments

No Known Activations