INDEX

Explanations

sequences indicating change or movement over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

awi

-0.16

erken

-0.16

ÏģÏħ

-0.15

amas

-0.14

-alist

-0.14

umbed

-0.14

Ã¤ll

-0.14

 Replacement

-0.14

orce

-0.14

POSITIVE LOGITS

 again

0.26

again

0.25

 Again

0.22

Again

0.22

 láº¡i

0.21

 novamente

0.20

 ëĭ¤ìĭľ

0.19

 ÑģÐ½Ð¾Ð²Ð°

0.19

 wieder

0.19

 weer

0.18

Activations Density 0.139%

sequences indicating change or movement over time

No Comments

No Known Activations