INDEX

Explanations

phrases indicating legal representation or law-related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 scri

-0.16

 memor

-0.15

eb

-0.15

åĬŀ

-0.14

yas

-0.14

IBE

-0.14

ebek

-0.14

aldi

-0.13

ngine

-0.13

ëį°ìĿ´íĬ¸

-0.13

POSITIVE LOGITS

ãĥ¼ãĥĸ

0.16

aliz

0.15

uff

0.15

0.14

icode

0.14

 enforce

0.14

.MixedReality

0.14

******↵

0.14

esto

0.13

Activations Density 0.005%

phrases indicating legal representation or law-related entities

No Comments

No Known Activations