INDEX

Explanations

words and terms related to food, dietary preferences, and culinary experiences

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

anta

-0.18

trand

-0.16

Ì§

-0.15

 conse

-0.14

oline

-0.14

tero

-0.14

dit

-0.14

oli

-0.14

anth

-0.14

POSITIVE LOGITS

yun

0.17

ÑıÐ³

0.16

ãĤ¤ãĥī

0.14

 navr

0.14

anni

0.14

 ÐĿÐ°Ñģ

0.13

ãģįãģŁ

0.13

etten

0.13

IFI

0.13

kits

0.13

Activations Density 0.031%

words and terms related to food, dietary preferences, and culinary experiences

No Comments

No Known Activations