INDEX

Explanations

specific formatting or punctuational patterns within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

CADE

-0.15

Sep

-0.14

drs

-0.14

afd

-0.14

 beck

-0.14

Ã¼ÄŁ

-0.13

à¸ªà¸³à¸Ļ

-0.13

datap

-0.13

Ã©rÃ©

-0.13

RequestId

-0.13

POSITIVE LOGITS

à¸¸à¸Ļà¸²à¸¢à¸Ļ

0.19

ruary

0.19

à¤Ĥà¤¬à¤°

0.19

Ø³ÙħØ¨Ø±

0.18

uary

0.18

æľĪ

0.17

à¸´à¸ģà¸²à¸¢à¸Ļ

0.17

embre

0.17

iembre

0.17

à¸²à¸¢à¸Ļ

0.16

Activations Density 0.050%

specific formatting or punctuational patterns within the text

No Comments

No Known Activations