INDEX

Explanations

mentions of chefs or culinary professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

dorf

-0.17

-toast

-0.15

gon

-0.14

auer

-0.14

 Mineral

-0.14

enity

-0.14

 PROT

-0.14

orida

-0.14

estructor

-0.14

itors

-0.13

POSITIVE LOGITS

plor

0.16

ieu

0.15

kin

0.15

æ¸Ī

0.14

iev

0.14

Flo

0.13

 Fate

0.13

ymbol

0.13

pawn

0.13

 Fight

0.13

Activations Density 0.004%

mentions of chefs or culinary professionals

No Comments

No Known Activations