INDEX

Explanations

actions and movements related to physical tasks or responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 favorable

-0.20

 unfavorable

-0.19

 catalogs

-0.18

 zipper

-0.17

 enrollment

-0.17

 Enrollment

-0.17

 upward

-0.16

 neighborhoods

-0.16

uki

-0.16

oriented

-0.16

POSITIVE LOGITS

 round

0.38

round

0.23

 forwards

0.22

 aged

0.22

 sens

0.22

 fraction

0.20

 Round

0.20

 ROUND

0.19

.round

0.19

 whilst

0.19

Activations Density 0.308%

actions and movements related to physical tasks or responsibilities

No Comments

No Known Activations