INDEX

Explanations

occurrences of the articles and prepositions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

arten

-0.18

 Prostitutas

-0.17

eteria

-0.16

iesta

-0.15

olist

-0.15

istence

-0.14

 jedna

-0.14

alace

-0.14

inue

-0.14

 conduc

-0.13

POSITIVE LOGITS

ito

0.24

 prÃ³p

0.21

seu

0.21

 primeiro

0.18

 Ãºltimo

0.18

 lado

0.16

itos

0.16

 mesmo

0.16

 Depart

0.16

 flux

0.16

Activations Density 0.012%

occurrences of the articles and prepositions in the text

No Comments

No Known Activations