INDEX

Explanations

words related to food, cooking, and hospitality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

.scalablytyped

-0.17

amu

-0.16

ule

-0.15

IPP

-0.15

ioned

-0.15

alah

-0.14

omu

-0.14

oupon

-0.14

OfWork

-0.13

FTA

-0.13

POSITIVE LOGITS

ephy

0.15

åĲĪãĤıãģĽ

0.15

wis

0.15

nict

0.14

erte

0.14

ogle

0.14

ven

0.13

ez

0.13

erne

0.13

aa

0.13

Activations Density 0.039%

words related to food, cooking, and hospitality

No Comments

No Known Activations