INDEX

Explanations

concepts related to well-being and body alignment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

legant

-0.14

 Reporter

-0.14

Î¯Î´Î±

-0.14

morgan

-0.14

eon

-0.14

ebin

-0.13

imp

-0.13

acomment

-0.13

Ordinal

-0.13

okit

-0.13

POSITIVE LOGITS

must

0.27

 Must

0.26

Must

0.26

 must

0.25

å¿ħé¡»

0.24

 å¿ħ

0.22

 MUST

0.21

requires

0.20

 requires

0.20

.must

0.20

Activations Density 0.093%

concepts related to well-being and body alignment

No Comments

No Known Activations