INDEX

Explanations

phrases related to legal rights and capabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Å¡ov

-0.17

URT

-0.16

eum

-0.15

arus

-0.14

MetaData

-0.14

 progressive

-0.14

olik

-0.13

Zd

-0.13

ilan

-0.13

 Investigations

-0.13

POSITIVE LOGITS

unc

0.16

ami

0.16

iani

0.14

byt

0.14

antro

0.13

agnost

0.13

 Feinstein

0.13

 Vance

0.13

acier

0.13

utsch

0.13

Activations Density 0.000%

phrases related to legal rights and capabilities

No Comments

No Known Activations