INDEX

Explanations

references to various "items" in a document, particularly those labeled or categorized as items

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

aber

-0.19

ven

-0.19

 Gallagher

-0.17

itz

-0.16

aver

-0.16

zeit

-0.16

icut

-0.15

loe

-0.14

RIEND

-0.14

en

-0.14

POSITIVE LOGITS

getter

0.19

Ã¼b

0.19

ennon

0.17

è´¨

0.17

åĢĳ

0.15

ÑĢÐ°Ð·Ñĥ

0.15

laus

0.15

ERRU

0.15

raÅ¾

0.15

ensity

0.14

Activations Density 0.040%

references to various "items" in a document, particularly those labeled or categorized as items

No Comments

No Known Activations