INDEX

Explanations

concepts related to the pursuit and misconceptions of happiness and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itten

-0.16

alled

-0.15

egrity

-0.15

alian

-0.15

 GRID

-0.14

opol

-0.14

arked

-0.14

Ð°Ð»Ð¾Ð¼

-0.13

ihad

-0.13

zia

-0.13

POSITIVE LOGITS

ä»¥ä¸º

0.33

 assume

0.33

 assumes

0.33

 assumption

0.31

 assuming

0.30

assume

0.30

 mistake

0.29

 assumed

0.28

 think

0.28

 THINK

0.28

Activations Density 0.647%

concepts related to the pursuit and misconceptions of happiness and well-being

No Comments

No Known Activations