INDEX

Explanations

mentions of fees and charges 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ness

-0.19

pin

-0.18

aneously

-0.18

nen

-0.16

specific

-0.16

maal

-0.16

weit

-0.15

net

-0.15

Ã¸d

-0.15

enment

-0.15

POSITIVE LOGITS

-paying

0.24

 charged

0.23

 structure

0.22

 paid

0.22

 Structure

0.21

 structures

0.20

 schedule

0.19

-paid

0.19

_paid

0.19

ble

0.19

Activations Density 0.029%

mentions of fees and charges in various contexts

No Comments

No Known Activations