INDEX

Explanations

names of people and notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

pest

-0.19

ening

-0.17

enna

-0.15

 Lena

-0.15

acity

-0.14

bs

-0.14

$$$$

-0.14

gos

-0.14

REN

-0.14

eman

-0.14

POSITIVE LOGITS

yw

0.17

isci

0.16

eÄį

0.15

asio

0.15

istrovstvÃŃ

0.15

ÙĪØ§Ø±Ùĩ

0.15

hum

0.15

cy

0.15

woord

0.14

nem

0.14

Activations Density 0.221%

names of people and notable figures

No Comments

No Known Activations