INDEX

Explanations

terms related to rotation and movement

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

onne

-0.17

irected

-0.17

iasi

-0.16

oner

-0.16

aid

-0.16

oa

-0.15

.UnitTesting

-0.15

lum

-0.15

oop

-0.15

 Maul

-0.15

POSITIVE LOGITS

ally

0.28

ALLY

0.21

0.19

about

0.19

atable

0.18

axis

0.18

als

0.18

 around

0.18

/trans

0.17

ational

0.17

Activations Density 0.028%

terms related to rotation and movement

No Comments

No Known Activations