INDEX

Explanations

references to maps and geographic information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Pictures

-0.16

 pictures

-0.15

allest

-0.15

 Location

-0.15

Location

-0.15

ovit

-0.14

Eve

-0.14

 location

-0.14

 viol

-0.14

Pictures

-0.14

POSITIVE LOGITS

 Sheet

0.27

 sheets

0.27

 Sheets

0.27

 cart

0.25

 scale

0.24

Sheet

0.24

-sheet

0.24

scale

0.23

 sheet

0.23

-scale

0.23

Activations Density 0.022%

references to maps and geographic information

No Comments

No Known Activations