INDEX

Explanations

possessive forms and phrases implying relationships or interactions involving individuals

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

uds

-0.17

hower

-0.17

uforia

-0.17

ÏģÎ¿Ïį

-0.16

lette

-0.16

elsing

-0.15

erialize

-0.15

į

-0.15

ë¶Ī

-0.15

rats

-0.14

POSITIVE LOGITS

0.17

 Cabr

0.16

0.15

aka

0.14

 gÃ¥r

0.14

 steady

0.14

abs

0.14

Activations Density 0.181%

possessive forms and phrases implying relationships or interactions involving individuals

No Comments

No Known Activations