INDEX

Explanations

references to physical locations and structures

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

Ð±Ð¾ÑĤ

-0.16

urb

-0.16

ossal

-0.14

ocab

-0.14

cult

-0.13

spark

-0.13

ROUT

-0.13

orget

-0.13

ä»¶

-0.13

ubic

-0.13

POSITIVE LOGITS

ble

0.29

 conc

0.28

 stands

0.28

 press

0.25

 suites

0.25

 upper

0.25

 premium

0.24

 grand

0.24

VIP

0.23

stands

0.23

Activations Density 0.022%

references to physical locations and structures

No Comments

No Known Activations