INDEX

Explanations

phrases related to discourse markers and sentence structure

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

 Sort

-0.16

.setResult

-0.15

ãģĦãģ¾ãģĻ

-0.14

Ñĳ

-0.13

 Seznam

-0.13

Å¥

-0.13

rane

-0.13

/de

-0.13

Ø§ÙĬØ§

-0.13

jac

-0.12

POSITIVE LOGITS

 what

0.74

what

0.60

 What

0.49

 whats

0.46

What

0.44

.what

0.44

 WHAT

0.41

ä»Ģä¹Ī

0.41

 Ø¢ÙĨÚĨÙĩ

0.40

WHAT

0.38

Activations Density 0.225%

phrases related to discourse markers and sentence structure

No Comments

No Known Activations