INDEX

Explanations

concepts related to legality and permissions in creative contexts

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

ohan

-0.16

enet

-0.15

ãģĹãģĭ

-0.14

deb

-0.14

omp

-0.14

 ÙĩÙĨÚ¯Ø§Ùħ

-0.14

lement

-0.14

azor

-0.14

Ð¾Ð±Ð¾Ð²

-0.14

aptor

-0.13

POSITIVE LOGITS

 provided

0.57

 Provided

0.52

 PROVIDED

0.50

 subject

0.47

provided

0.47

åıªè¦ģ

0.43

subject

0.39

 Subject

0.37

Subject

0.35

 assuming

0.32

Activations Density 0.337%

concepts related to legality and permissions in creative contexts

No Comments

No Known Activations