INDEX

Explanations

references to specific authors and their works

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

unication

-0.18

 essentials

-0.15

íķĳ

-0.14

%"

-0.14

Guy

-0.14

[assembly

-0.14

ëŀĳ

-0.13

isateur

-0.13

itch

-0.13

tes

-0.13

POSITIVE LOGITS

UDO

0.20

quisar

0.18

segue

0.18

ilent

0.17

udo

0.17

quisa

0.17

uliar

0.15

scri

0.15

ado

0.15

Activations Density 0.012%

references to specific authors and their works

No Comments

No Known Activations