INDEX

Explanations

references to notable films and cinematic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

illaume

-0.17

abay

-0.17

resenter

-0.15

urch

-0.15

 XMLHttpRequest

-0.15

urum

-0.15

 Blasio

-0.14

kees

-0.14

ContentLoaded

-0.14

Ã¡bado

-0.14

POSITIVE LOGITS

 Kimber

0.16

loc

0.15

ucher

0.15

 headquarters

0.15

HQ

0.15

 famously

0.14

 cruc

0.14

_here

0.14

 future

0.14

 famous

0.13

Activations Density 0.112%

references to notable films and cinematic locations

No Comments

No Known Activations