INDEX

Explanations

concepts related to knowledge representation and organization within systems

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

-0.16

 ident

-0.15

JS

-0.15

 Sage

-0.15

-0.14

Du

-0.14

cr

-0.14

POSITIVE LOGITS

 Knowledge

0.27

knowledge

0.26

 knowledge

0.26

Knowledge

0.23

Ont

0.23

Ont

0.22

.semantic

0.21

nowledge

0.21

onto

0.19

 deduct

0.19

Activations Density 0.063%

concepts related to knowledge representation and organization within systems

No Comments

No Known Activations