INDEX

Explanations

expressions related to saving and retrieving data or information

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

une

-0.15

æļ

-0.14

ropp

-0.14

å¥Ī

-0.14

asher

-0.14

unker

-0.13

.descriptor

-0.13

UNE

-0.13

ÑĦÐ¸

-0.13

ino

-0.13

POSITIVE LOGITS

 later

0.35

later

0.27

 Later

0.25

Later

0.25

 spÃ¤ter

0.24

 future

0.23

 whenever

0.23

future

0.20

 retrieval

0.20

 anytime

0.19

Activations Density 0.200%

expressions related to saving and retrieving data or information

No Comments

No Known Activations