INDEX

Explanations

symbols, numbers, and mathematical operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ob

-0.24

Ob

-0.21

Âłob

-0.18

-ob

-0.18

_ob

-0.17

Ob

-0.17

OB

-0.16

ifu

-0.16

Å¡ov

-0.16

 Kushner

-0.16

POSITIVE LOGITS

0.33

 obvious

0.33

0.28

 apparent

0.27

 evident

0.27

0.26

0.24

0.23

Activations Density 0.038%

symbols, numbers, and mathematical operations

No Comments

No Known Activations