INDEX

Explanations

definitions and explanations of concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

zers

-0.14

 correspond

-0.14

ÐºÐ¾Ð³

-0.14

verb

-0.13

imd

-0.13

amm

-0.13

alez

-0.13

orama

-0.13

ffects

-0.13

onder

-0.13

POSITIVE LOGITS

 definition

0.29

 definitions

0.23

 Definition

0.22

definition

0.22

Definition

0.21

 success

0.20

 truly

0.19

definitions

0.18

Definitions

0.18

-definition

0.18

Activations Density 0.166%

definitions and explanations of concepts

No Comments

No Known Activations