INDEX

Explanations

terms related to patrons and patents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

tracks

-0.18

eries

-0.16

ICI

-0.15

omat

-0.15

 Shank

-0.15

-0.14

orer

-0.14

ivant

-0.14

placements

-0.14

ubern

-0.14

POSITIVE LOGITS

ience

0.24

ernity

0.22

rice

0.21

ricia

0.20

ting

0.19

 Pending

0.18

ron

0.18

agon

0.18

riz

0.18

erno

0.17

Activations Density 0.023%

terms related to patrons and patents

No Comments

No Known Activations