INDEX

Explanations

terms related to court procedures and legal contexts

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

 prosecute

-0.16

ULLET

-0.15

 Prosec

-0.15

ãģıãĤĮ

-0.14

.ms

-0.14

ÐµÐ²Ð¸Ñĩ

-0.14

 pros

-0.14

udit

-0.14

 prosecutions

-0.14

 task

-0.14

POSITIVE LOGITS

aylight

0.18

sez

0.17

erli

0.15

ÏĦÏĮ

0.15

 backlog

0.15

æ£

0.15

Align

0.14

gili

0.14

/cs

0.14

ickname

0.14

Activations Density 0.172%

terms related to court procedures and legal contexts

No Comments

No Known Activations