INDEX

Explanations

the repeated word "na," likely indicating a specific language or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ruk

-0.16

Ø§Ø¯ÙĬØ©

-0.14

 Metodo

-0.14

Guy

-0.14

kke

-0.14

irty

-0.14

outh

-0.14

agu

-0.13

vek

-0.13

cep

-0.13

POSITIVE LOGITS

Ã©rÃ©

0.15

 phÃ³ng

0.14

uelle

0.14

 Junior

0.14

rouch

0.13

rello

0.13

 Bach

0.13

ardon

0.13

ãĤ·ãĥ§

0.13

Activations Density 0.002%

the repeated word "na," likely indicating a specific language or context

No Comments

No Known Activations