INDEX

Explanations

specific identifiers or metrics related to data and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

opc

-0.17

uala

-0.16

 Ð¿Ð¾Ñħ

-0.16

gesi

-0.16

dings

-0.16

jez

-0.15

eket

-0.15

ahrung

-0.15

ButtonText

-0.15

Falsy

-0.14

POSITIVE LOGITS

ban

0.48

ban

0.32

iban

0.30

ben

0.30

aban

0.28

ba

0.25

Ban

0.24

Ban

0.23

-b

0.23

umb

0.22

Activations Density 0.002%

specific identifiers or metrics related to data and analysis

No Comments

No Known Activations