INDEX

Explanations

references to legal proceedings and sentencing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 arrests

-0.19

allas

-0.17

 Arrest

-0.17

usercontent

-0.17

 arrest

-0.16

PageIndex

-0.16

-0.15

 misdemeanor

-0.15

udit

-0.15

POSITIVE LOGITS

capital

0.20

 capital

0.19

death

0.18

 death

0.17

Capital

0.17

odesk

0.17

hood

0.17

-death

0.16

 Death

0.16

 ÑģÐ¼ÐµÑĢ

0.15

Activations Density 0.027%

references to legal proceedings and sentencing

No Comments

No Known Activations