INDEX

Explanations

instances of the prefix "fl" indicating various states or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Gibson

-0.15

oved

-0.15

ANTE

-0.15

undler

-0.14

esser

-0.14

bol

-0.14

iaz

-0.14

ymce

-0.14

quet

-0.14

ius

-0.14

POSITIVE LOGITS

fl

0.34

ipp

0.23

uster

0.21

ims

0.21

uff

0.20

atter

0.17

ounce

0.17

 Flame

0.17

ollo

0.17

rst

0.16

Activations Density 0.014%

instances of the prefix "fl" indicating various states or conditions

No Comments

No Known Activations