INDEX

Explanations

phrases indicating legal judgments or findings of guilt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

avra

-0.19

ebek

-0.18

ADOS

-0.16

uele

-0.16

ARIABLE

-0.15

 oblig

-0.15

ãģŀ

-0.15

ë¡±

-0.15

laÄį

-0.15

ivid

-0.14

POSITIVE LOGITS

fit

0.35

Fit

0.28

 guilty

0.28

Fit

0.27

-fit

0.26

fit

0.26

 fitness

0.23

 unfit

0.23

 worthy

0.21

.fit

0.20

Activations Density 0.091%

phrases indicating legal judgments or findings of guilt

No Comments

No Known Activations