INDEX

Explanations

technical references and components related to software interfaces and functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

/Table

-0.14

LOUR

-0.14

 garn

-0.14

ãĤ¢ãĥ³

-0.14

Ú¯Ø§ÙĨ

-0.14

ign

-0.13

gem

-0.13

 Garn

-0.13

nger

-0.13

.Resume

-0.13

POSITIVE LOGITS

 window

0.53

window

0.44

çªĹ

0.43

-window

0.40

 windows

0.38

_window

0.36

 dialog

0.36

 Window

0.35

Window

0.34

.window

0.33

Activations Density 0.153%

technical references and components related to software interfaces and functionalities

No Comments

No Known Activations