INDEX

Explanations

content related to spoilers in films and series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ë³¸

-0.16

uder

-0.16

acles

-0.15

aller

-0.15

andas

-0.15

peare

-0.15

çĴ°

-0.15

 BASIS

-0.14

orman

-0.14

:checked

-0.14

POSITIVE LOGITS

oni

0.16

fx

0.15

resi

0.14

Bra

0.14

heim

0.14

istem

0.14

 Folk

0.14

 Fetish

0.14

Ð¾Ð»Ð¾Ð´

0.14

Activations Density 0.298%

content related to spoilers in films and series

No Comments

No Known Activations