INDEX

Explanations

words associated with various types of food and beverages, particularly in a dining or hospitality context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

.FontStyle

-0.18

à¸§à¸¥

-0.17

uble

-0.15

hong

-0.15

 abandon

-0.14

oller

-0.14

use

-0.14

 Sites

-0.14

 Bris

-0.13

 uses

-0.13

POSITIVE LOGITS

 selection

0.24

selection

0.23

 selections

0.21

 offerings

0.21

 Selection

0.21

 choices

0.21

choices

0.21

-selection

0.21

Offer

0.19

 offered

0.19

Activations Density 0.152%

words associated with various types of food and beverages, particularly in a dining or hospitality context

No Comments

No Known Activations