INDEX

Explanations

legal terminology related to court judgments and appeals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

CUS

-0.16

 WARRANT

-0.15

 mÃ¡t

-0.15

kaar

-0.15

haft

-0.15

isposable

-0.14

Ð°ÐºÑģÐ¸Ð¼

-0.14

 Plaintiff

-0.14

/GPL

-0.14

 prosecutions

-0.13

POSITIVE LOGITS

 appeal

0.77

 Appeal

0.65

 appeals

0.65

appe

0.61

 appealed

0.57

 appealing

0.56

 Appeals

0.54

Appe

0.53

 Appe

0.44

 appe

0.35

Activations Density 0.179%

legal terminology related to court judgments and appeals

No Comments

No Known Activations