INDEX

Explanations

technical terms and components related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

fram

-0.16

quin

-0.15

ergy

-0.15

nia

-0.14

 Scar

-0.14

ACS

-0.14

ãĥ¼ãĥ«ãĥī

-0.14

assed

-0.14

anca

-0.14

POSITIVE LOGITS

ariant

0.14

ä½

0.14

mund

0.14

/apt

0.14

.dw

0.13

atab

0.13

deb

0.13

akeup

0.13

udy

0.13

_LOGGER

0.13

Activations Density 0.039%

technical terms and components related to programming and software development

No Comments

No Known Activations