INDEX

Explanations

references to the "Star Wars" film series and its related productions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ãģĴ

-0.16

ÑĢÐ°Ð´Ð¸

-0.16

.sponge

-0.15

rne

-0.15

NTN

-0.15

-0.14

é½Ĳ

-0.14

à¸¸à¸Ķ

-0.14

 scheme

-0.13

 Tiger

-0.13

POSITIVE LOGITS

 Star

0.19

 Skywalker

0.18

Star

0.17

Han

0.17

STAR

0.16

 Spielberg

0.16

 Harrison

0.16

 Chew

0.16

 Abrams

0.15

Resistance

0.15

Activations Density 0.084%

references to the "Star Wars" film series and its related productions

No Comments

No Known Activations