INDEX

Explanations

references to theatrical works and their details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

velt

-0.17

 overd

-0.15

Framework

-0.15

ìĹĦ

-0.15

 Slate

-0.15

æľīéĻĲ

-0.15

repid

-0.15

_Base

-0.15

à¹ĩà¸ĩ

-0.14

Pew

-0.14

POSITIVE LOGITS

 Eugene

0.20

Nab

0.19

Tos

0.19

Fal

0.19

 Norm

0.18

 Lucia

0.18

Ot

0.17

 Dialog

0.17

Peer

0.17

Fa

0.16

Activations Density 0.012%

references to theatrical works and their details

No Comments

No Known Activations