INDEX

Explanations

information about artists, their backgrounds, and their works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Psychology

-0.18

 Photography

-0.18

 physiology

-0.17

 sÃ´ng

-0.16

alon

-0.16

Coding

-0.16

iology

-0.16

 physics

-0.16

 detach

-0.15

 Physiology

-0.15

POSITIVE LOGITS

 sculpt

0.21

 practicing

0.20

 designer

0.20

 accomplished

0.19

 drafts

0.18

-cart

0.18

 traged

0.18

 gifted

0.18

 scen

0.17

 theoret

0.17

Activations Density 0.273%

information about artists, their backgrounds, and their works

No Comments

No Known Activations