INDEX

Explanations

terms related to beginners and novice levels in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÙĪÙĦÙĬ

-0.15

usi

-0.15

CRET

-0.14

ÐµÐ´Ð¸Ð½Ð¸

-0.14

ady

-0.14

erli

-0.14

unk

-0.14

edBy

-0.14

aban

-0.14

ced

-0.14

POSITIVE LOGITS

/new

0.21

/basic

0.20

/welcome

0.20

/original

0.19

-stage

0.19

 orientation

0.18

-level

0.18

/Foundation

0.18

 stage

0.18

 stages

0.17

Activations Density 0.059%

terms related to beginners and novice levels in various contexts

No Comments

No Known Activations