INDEX

Explanations

words related to recognition, understanding, and action in the context of learning and behavior management

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

elta

-0.16

iska

-0.14

agn

-0.14

uc

-0.14

adas

-0.14

hic

-0.14

anken

-0.13

imu

-0.13

Ì

-0.13

å§¿

-0.13

POSITIVE LOGITS

it

0.44

 them

0.39

å®ĥ

0.34

them

0.31

 nÃ³

0.29

 Ð¾Ð½Ð¾

0.26

 Ø¢ÙĨ

0.24

itu

0.23

it

0.23

 ê·¸ê²ĥ

0.23

Activations Density 0.482%

words related to recognition, understanding, and action in the context of learning and behavior management

No Comments

No Known Activations