INDEX

Explanations

abbreviations or acronyms that represent organizations or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

onn

-0.15

 Marketable

-0.14

usi

-0.14

terra

-0.14

å»Ĭ

-0.14

 ØªØ²

-0.14

 VÅ¡ech

-0.14

ipop

-0.13

lok

-0.13

Éµ

-0.13

POSITIVE LOGITS

 sack

0.16

aid

0.15

¼åĲĪ

0.15

ovna

0.15

Å¡li

0.14

GLOSS

0.14

imon

0.14

iano

0.14

ator

0.14

haus

0.14

Activations Density 0.059%

abbreviations or acronyms that represent organizations or concepts

No Comments

No Known Activations