INDEX

Explanations

themes related to historical analysis and the evolution of ideas

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

esel

-0.18

è§

-0.16

asso

-0.14

éĨ

-0.13

Hierarchy

-0.13

 correct

-0.13

rompt

-0.13

Descriptors

-0.13

 Ð¿ÑĢÐµÐ´ÑĥÑģ

-0.13

ÙĦÛĮØª

-0.12

POSITIVE LOGITS

 ways

0.24

 persistence

0.23

 intersections

0.22

 rise

0.22

 question

0.21

 lived

0.21

 contested

0.20

 disc

0.20

leg

0.20

 relationship

0.19

Activations Density 0.155%

themes related to historical analysis and the evolution of ideas

No Comments

No Known Activations