INDEX

Explanations

discussions related to technical specifications and functionalities of systems and software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Contributor

-0.15

.helpers

-0.14

EqualityComparer

-0.13

åĬłå·¥

-0.13

ild

-0.13

ildo

-0.13

ĽĦ

-0.12

oultry

-0.12

alÄ±

-0.12

edu

-0.12

POSITIVE LOGITS

 support

0.98

 supports

0.85

support

0.85

 Support

0.84

Support

0.81

æĶ¯æĮģ

0.81

-support

0.79

 SUPPORT

0.78

 supported

0.75

_support

0.74

Activations Density 0.400%

discussions related to technical specifications and functionalities of systems and software

No Comments

No Known Activations