INDEX

Explanations

terminologies related to scientific reasoning and philosophical discourse

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

elu

-0.17

æģ¯

-0.15

typeorm

-0.15

uo

-0.14

leftright

-0.14

 primal

-0.14

 Accent

-0.14

dech

-0.13

icode

-0.13

 titan

-0.13

POSITIVE LOGITS

 fals

0.28

 induction

0.26

 deduct

0.24

 statements

0.23

emp

0.23

Pop

0.23

 observation

0.22

 observations

0.21

Ded

0.21

 experimentation

0.20

Activations Density 0.183%

terminologies related to scientific reasoning and philosophical discourse

No Comments

No Known Activations