INDEX

Explanations

universal truths or concepts that apply to all beings or situations

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

ÑģÑı

-0.17

pec

-0.16

 Peng

-0.15

-0.14

SelectedItem

-0.14

DOT

-0.14

Ø³ÙĪ

-0.14

edu

-0.14

noch

-0.13

POSITIVE LOGITS

 manner

0.19

 creation

0.18

 else

0.17

odial

0.17

men

0.17

creation

0.16

 Creation

0.16

 knowledge

0.16

 that

0.16

that

0.15

Activations Density 0.087%

universal truths or concepts that apply to all beings or situations

No Comments

No Known Activations