INDEX

Explanations

phrases that indicate usage or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ships

-0.17

 Furious

-0.16

zo

-0.14

Ø²ÙĪ

-0.14

ician

-0.14

 Cran

-0.14

eck

-0.14

	Copyright

-0.14

iPad

-0.14

ship

-0.13

POSITIVE LOGITS

DataManager

0.15

anst

0.14

obus

0.14

UNT

0.14

ãĤĵ

0.14

pyx

0.14

 Ø¨ÙĪØ§Ø¨Ø©

0.14

ideos

0.13

_InitStructure

0.13

Activations Density 0.030%

phrases that indicate usage or purpose

No Comments

No Known Activations