INDEX

Explanations

possessive forms and indicators of ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.21

issen

-0.15

uilder

-0.14

 Wage

-0.14

ETHER

-0.14

-0.13

onne

-0.13

atoria

-0.13

 cÃ©lib

-0.13

poons

-0.13

POSITIVE LOGITS

 ability

0.19

 efforts

0.17

 role

0.16

 attempt

0.16

 attempts

0.15

Ð³Ñĥ

0.15

use

0.15

 ÑģÐ¿Ð¾ÑģÐ¾Ð±

0.15

usc

0.15

Activations Density 0.205%

possessive forms and indicators of ownership

No Comments

No Known Activations