INDEX

Explanations

terms related to cooking and food preparation

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

endor

-0.16

estre

-0.16

nik

-0.15

ys

-0.15

assis

-0.14

oyer

-0.14

ÑİÐº

-0.14

ny

-0.14

urg

-0.14

ä¸¹

-0.14

POSITIVE LOGITS

.pub

0.17

AccessType

0.15

ehler

0.15

osc

0.14

atel

0.14

kÃ¼

0.14

stery

0.14

 Sanford

0.14

æķ

0.13

Activations Density 0.007%

terms related to cooking and food preparation

No Comments

No Known Activations