INDEX

Explanations

specific names of individuals 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ftware

-0.16

Interop

-0.15

ssql

-0.15

udad

-0.15

ÑĩÐ½Ð°

-0.14

_ABS

-0.14

imei

-0.14

ori

-0.14

yiy

-0.14

Ð²ÐµÑĤ

-0.14

POSITIVE LOGITS

 John

0.22

John

0.18

 john

0.18

 JOHN

0.17

 meta

0.15

ÏĥÎ¼

0.15

 Johnny

0.14

 cast

0.14

 Brennan

0.14

ardown

0.14

Activations Density 0.065%

specific names of individuals and notable figures

No Comments

No Known Activations