INDEX

Explanations

references to specific films and their related media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ÑĢÐ¾Ñĩ

-0.16

 eBooks

-0.14

 Ivanka

-0.14

SCRIBE

-0.14

 TValue

-0.13

gte

-0.13

à¸ªà¸²à¸£

-0.13

 Ø¨Ù¾

-0.13

IDEOS

-0.13

 Webcam

-0.13

POSITIVE LOGITS

 Lobby

0.29

 lobby

0.29

 Fold

0.28

 folded

0.28

 Poster

0.26

 fold

0.25

 poster

0.25

 Rolled

0.24

 folds

0.23

lobby

0.23

Activations Density 0.005%

references to specific films and their related media content

No Comments

No Known Activations