INDEX

Explanations

terms related to negative thought patterns and the importance of positive affirmations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ythe

-0.14

ãĤ°ãĥ©

-0.14

rawer

-0.14

.tool

-0.14

ëŀĳ

-0.14

 èŃ

-0.13

sr

-0.13

duk

-0.13

ãĥ¡ãĥ©

-0.13

song

-0.13

POSITIVE LOGITS

 utter

0.42

utter

0.37

say

0.32

 saying

0.29

Ut

0.28

 said

0.28

SAY

0.28

rec

0.27

ut

0.27

Say

0.26

Activations Density 0.336%

terms related to negative thought patterns and the importance of positive affirmations

No Comments

No Known Activations