INDEX

Explanations

references to structure and organization of hierarchical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-readable

-0.15

 univers

-0.15

stick

-0.15

 mest

-0.14

ain

-0.14

Ø±Ø§ÙĨÙĩ

-0.14

.cls

-0.14

seys

-0.14

Ø®Ø´

-0.14

entication

-0.14

POSITIVE LOGITS

bett

0.17

 count

0.15

-Ta

0.15

OfType

0.15

 convenience

0.14

mor

0.14

PIL

0.14

 rele

0.13

Partner

0.13

 åĦ

0.13

Activations Density 0.052%

references to structure and organization of hierarchical data

No Comments

No Known Activations