INDEX

Explanations

references to judicial roles and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

chet

-0.15

 Fate

-0.14

Sah

-0.14

Å¡tÄĽ

-0.14

 kalk

-0.13

 Milk

-0.13

 wind

-0.13

å¯

-0.13

chl

-0.13

gaard

-0.13

POSITIVE LOGITS

 court

0.25

-court

0.23

 cour

0.23

 dock

0.23

cour

0.22

 circuit

0.22

Court

0.22

 Cour

0.22

bench

0.22

Cour

0.22

Activations Density 0.051%

references to judicial roles and functions

No Comments

No Known Activations