INDEX

Explanations

information related to television shows and their airings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

pector

-0.17

ÐµÑĤÑĮÑģÑı

-0.14

 Wahl

-0.14

aukee

-0.14

inema

-0.14

Ø§ÙĨÙĪ

-0.13

iaux

-0.13

åĭ¢

-0.13

steller

-0.13

antry

-0.13

POSITIVE LOGITS

air

0.61

air

0.54

-air

0.52

 airs

0.52

 aired

0.50

 airing

0.47

airs

0.44

 aire

0.43

Air

0.42

_air

0.42

Activations Density 0.353%

information related to television shows and their airings

No Comments

No Known Activations