INDEX

Explanations

descriptors related to quality and suitability of products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

anzi

-0.15

-0.14

oppers

-0.14

 courtesy

-0.14

embali

-0.14

áº¯ng

-0.14

abei

-0.13

orias

-0.13

ymes

-0.13

nette

-0.13

POSITIVE LOGITS

 choice

0.23

 when

0.19

choice

0.19

/use

0.18

 choices

0.18

 whether

0.17

 option

0.17

when

0.17

used

0.17

 WHEN

0.17

Activations Density 0.091%

descriptors related to quality and suitability of products

No Comments

No Known Activations