INDEX

Explanations

parentheses and their variations in text

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

ãĥªãĥ¼ãĤº

-0.15

Ä¢

-0.14

auc

-0.14

olumn

-0.14

 nhiÃªn

-0.14

 ...(

-0.13

brig

-0.13

abis

-0.13

ppard

-0.13

vie

-0.13

POSITIVE LOGITS

atab

0.15

incinn

0.14

aka

0.14

LEX

0.14

umps

0.14

'gc

0.14

Â±

0.14

ifax

0.14

Rip

0.13

-navbar

0.13

Activations Density 0.437%

parentheses and their variations in text

No Comments

No Known Activations