INDEX

Explanations

specific technical and operational terms related to healthcare and safety measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

avras

-0.15

ÑĥÐ´Ð¸

-0.15

á»įng

-0.14

à¥ģà¤¬

-0.14

yster

-0.14

Ð¾Ð³Ð¾Ð´

-0.14

uba

-0.14

inely

-0.14

 Arial

-0.14

PRS

-0.14

POSITIVE LOGITS

amic

0.16

Tar

0.15

âĦ

0.15

Tar

0.14

 Ventura

0.14

ILT

0.14

olt

0.14

 Nolan

0.14

ove

0.14

à¹Ģà¸§

0.14

Activations Density 0.001%

specific technical and operational terms related to healthcare and safety measures

No Comments

No Known Activations