INDEX

Explanations

references to households and families in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

frei

-0.17

enberg

-0.17

æľį

-0.15

,eg

-0.15

ÏĢÎ·

-0.14

oÄŁ

-0.14

adera

-0.14

.fromFunction

-0.14

ked

-0.14

ianne

-0.14

POSITIVE LOGITS

 Holly

0.17

 -*-č↵

0.15

Ã¡ng

0.14

/group

0.14

ss

0.13

ÑģÑĤÑĮ

0.13

eci

0.13

IBLE

0.13

bid

0.13

/single

0.13

Activations Density 0.038%

references to households and families in various contexts

No Comments

No Known Activations