INDEX

Explanations

technical terms and coding elements related to software and databases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

âĢ¦↵

-0.18

...↵

-0.16

âĢ¦

-0.16

Âł

-0.16

 âĢ¦↵

-0.15

“

-0.15

âĢ¦)

-0.15

amp

-0.15

 âĢ¦

-0.15

—"

-0.15

POSITIVE LOGITS

opcion

0.15

jedn

0.15

kelas

0.15

Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

0.14

InParameter

0.14

ovky

0.14

$MESS

0.14

'gc

0.14

Ð¾ÑĢÐ°Ñı

0.14

reopen

0.14

Activations Density 5.952%

technical terms and coding elements related to software and databases

No Comments

No Known Activations