INDEX

Explanations

phrases indicative of legal or regulatory language

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

cab

-0.18

Cab

-0.16

Cab

-0.15

emmel

-0.15

cab

-0.15

inar

-0.15

ajar

-0.15

 Needle

-0.14

acro

-0.14

xea

-0.14

POSITIVE LOGITS

ë§¥

0.15

Ð¼ÐµÑĢÐ¸ÐºÐ°Ð½

0.14

inkel

0.14

eneg

0.14

ŀ

0.14

lero

0.14

elah

0.14

 mant

0.14

.statusText

0.14

usi

0.13

Activations Density 0.001%

phrases indicative of legal or regulatory language

No Comments

No Known Activations