INDEX

Explanations

content related to legal and regulatory processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ji

-0.15

ÑĥÐ»Ð°

-0.15

ä»ĺ

-0.15

 nowhere

-0.14

ivamente

-0.14

IFT

-0.14

aliz

-0.14

è»¢

-0.14

POSITIVE LOGITS

.sample

0.16

istr

0.16

pool

0.16

 sample

0.15

atoire

0.15

amples

0.14

sample

0.14

 Cecil

0.14

orph

0.14

CHANT

0.14

Activations Density 0.802%

content related to legal and regulatory processes

No Comments

No Known Activations