INDEX

Explanations

references to scientific or statistical data sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

/unit

-0.14

 Ø§ÙĦÙĤØ¯

-0.14

addtogroup

-0.14

ãĥ³ãĥĸ

-0.14

.SC

-0.14

á»Ļ

-0.14

 Ø§ÙĦØ§ÙĨØª

-0.14

 kaps

-0.14

 nackte

-0.14

ÑĨÑĸ

-0.14

POSITIVE LOGITS

 Sloan

0.20

 faint

0.17

acc

0.17

 Amateur

0.17

Sof

0.16

 stars

0.16

CMD

0.15

å²ģ

0.15

 Pier

0.15

 dred

0.15

Activations Density 0.032%

references to scientific or statistical data sources

No Comments

No Known Activations