INDEX

Explanations

temporal references indicating recent timeframes

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

è£ľ

-0.14

à¸´à¹ī

-0.14

 resp

-0.14

oya

-0.13

ily

-0.13

ing

-0.13

VES

-0.13

 radiator

-0.13

 Merry

-0.13

ingen

-0.13

POSITIVE LOGITS

HeaderCode

0.16

DataExchange

0.15

GenerationStrategy

0.15

DDS

0.15

/MPL

0.14

aeper

0.14

/on

0.14

igu

0.14

.bunifuFlatButton

0.14

ummings

0.14

Activations Density 0.177%

temporal references indicating recent timeframes

No Comments

No Known Activations