INDEX

Explanations

references to popular culture, specifically relating to literary genres and food items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

apon

-0.15

onen

-0.14

oth

-0.14

stro

-0.14

esta

-0.14

wares

-0.14

indy

-0.13

 groom

-0.13

YP

-0.13

utas

-0.13

POSITIVE LOGITS

noinspection

0.15

inish

0.14

ighted

0.14

jeta

0.14

entionPolicy

0.14

à¥įà¤¤à¤µ

0.14

jo

0.13

Ú©ØªØ±

0.13

 trad

0.13

 Gallagher

0.13

Activations Density 0.025%

references to popular culture, specifically relating to literary genres and food items

No Comments

No Known Activations