INDEX

Explanations

terms related to nutritional health and food

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

minent

-0.15

 downs

-0.14

 Pont

-0.14

Tao

-0.14

lluminate

-0.14

 Petit

-0.14

 younger

-0.14

bons

-0.13

arp

-0.13

Ð°ÐºÐ¾Ð²

-0.13

POSITIVE LOGITS

Æ°ng

0.18

jed

0.16

immel

0.16

-HT

0.16

drs

0.15

vr

0.14

xis

0.14

anz

0.14

Č↵

0.14

kip

0.13

Activations Density 0.072%

terms related to nutritional health and food

No Comments

No Known Activations