INDEX

Explanations

references to user interactions and system functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Å¡ov

-0.17

å¤§åħ¨

-0.15

advance

-0.14

.IContainer

-0.13

ahoma

-0.13

Advance

-0.13

-aged

-0.13

pok

-0.13

facet

-0.13

dated

-0.12

POSITIVE LOGITS

 available

0.27

 offered

0.24

 observed

0.22

 involved

0.21

Obs

0.21

 desired

0.21

 provided

0.21

obs

0.20

 obtained

0.20

obs

0.20

Activations Density 0.047%

references to user interactions and system functionalities

No Comments

No Known Activations