INDEX

Explanations

specific details about film productions and prominent actors involved

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

anced

-0.17

Ì£

-0.15

/cgi

-0.15

kle

-0.14

inh

-0.14

 Simon

-0.14

Chooser

-0.14

Î±Î¹

-0.14

strcasecmp

-0.14

roit

-0.14

POSITIVE LOGITS

 Heard

0.36

 Amber

0.27

 Pirates

0.23

 Johnny

0.23

 amber

0.23

Johnny

0.22

amber

0.21

 heard

0.18

 Fairfax

0.17

 Hearing

0.17

Activations Density 0.004%

specific details about film productions and prominent actors involved

No Comments

No Known Activations