INDEX

Explanations

food-related terms and ingredients in recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Cov

-0.16

 sens

-0.16

Som

-0.15

otas

-0.15

ashi

-0.15

 Citizenship

-0.15

Gos

-0.14

som

-0.14

 Companion

-0.14

FINITY

-0.14

POSITIVE LOGITS

Ð½Ð¸Ñİ

0.16

 norge

0.16

atron

0.15

ëłµ

0.15

vat

0.15

ÏģÎ³

0.14

_digest

0.14

ecz

0.14

é§Ĩ

0.14

/window

0.14

Activations Density 0.085%

food-related terms and ingredients in recipes

No Comments

No Known Activations