INDEX

Explanations

references to ongoing commitments and subscription models

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

ILA

-0.15

chos

-0.14

å®¢

-0.14

 UNUSED

-0.14

aug

-0.14

éĥ¡

-0.14

_leg

-0.14

avian

-0.13

UILT

-0.13

İ

-0.13

POSITIVE LOGITS

 steady

0.18

 ongoing

0.18

à¸Ľà¸£à¸°à¸Īà¸³

0.17

 continuous

0.16

continuous

0.16

 forever

0.15

 daily

0.15

steady

0.15

 regular

0.15

Ð¾ÑĤÑĮ

0.15

Activations Density 0.352%

references to ongoing commitments and subscription models

No Comments

No Known Activations