INDEX

Explanations

references to Supreme Court nominations and judicial decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

kok

-0.18

readcr

-0.17

 Defaults

-0.15

.providers

-0.15

?>/

-0.15

ãģĭãģ£ãģŁ

-0.14

icom

-0.14

hait

-0.14

oren

-0.14

ActiveSheet

-0.13

POSITIVE LOGITS

SC

0.44

 justices

0.41

 Supreme

0.40

 Justice

0.40

 Chief

0.36

SC

0.35

Justice

0.34

(SC

0.33

 Court

0.33

 justice

0.32

Activations Density 0.147%

references to Supreme Court nominations and judicial decisions

No Comments

No Known Activations