INDEX

Explanations

characteristics related to food, specifically dish descriptions and culinary contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

rag

-0.21

linger

-0.19

erokee

-0.16

uters

-0.15

CardBody

-0.15

regor

-0.15

edBy

-0.14

bib

-0.14

olu

-0.14

erce

-0.14

POSITIVE LOGITS

 both

0.15

oret

0.15

0.14

both

0.14

Ð±ÑĥÐ´ÑĮ

0.13

ayah

0.13

 Janet

0.13

ay

0.13

0.12

plits

0.12

Activations Density 0.115%

characteristics related to food, specifically dish descriptions and culinary contexts

No Comments

No Known Activations