INDEX

Explanations

quotations or references to notable figures and their remarks

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

resa

-0.16

ostel

-0.15

enet

-0.15

enou

-0.15

 Ð¿Ð¾Ð´

-0.14

Ĥ¬

-0.14

éĲĺ

-0.14

zel

-0.14

izin

-0.13

æĪĴ

-0.13

POSITIVE LOGITS

ahlen

0.14

PRESSION

0.14

çħ

0.13

acha

0.13

 coherence

0.13

HITE

0.13

oad

0.13

ollo

0.13

caffe

0.13

æĥł

0.13

Activations Density 0.027%

quotations or references to notable figures and their remarks

No Comments

No Known Activations