INDEX

Explanations

information about new and notable places or events in a city

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

rott

-0.15

 Buen

-0.15

zon

-0.15

battle

-0.14

imitives

-0.14

 explo

-0.14

 Microsystems

-0.14

ernals

-0.14

Ø¨ØŃ

-0.14

 unleashed

-0.14

POSITIVE LOGITS

 Hakk

0.18

Ace

0.17

Ace

0.17

 Mandarin

0.16

 Crosby

0.16

 Bulg

0.16

LOUD

0.16

Nob

0.16

 Neue

0.16

 pent

0.15

Activations Density 0.075%

information about new and notable places or events in a city

No Comments

No Known Activations