INDEX

Explanations

references to visibility and recognition in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

anki

-0.15

ãĤ£

-0.14

allax

-0.14

ÑĢÑĥÐ·

-0.13

ama

-0.13

anner

-0.13

Pek

-0.13

finity

-0.13

ÑįÐ¹

-0.13

tu

-0.13

POSITIVE LOGITS

 seen

0.27

Seen

0.25

 sightings

0.24

seen

0.24

 appearing

0.22

 sighting

0.22

 Seen

0.22

 appeared

0.22

 frequent

0.21

 spotted

0.20

Activations Density 0.191%

references to visibility and recognition in various contexts

No Comments

No Known Activations