INDEX

Explanations

concepts related to recommendations and evaluations of products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

gress

-0.17

piar

-0.16

 subs

-0.15

 AppleWebKit

-0.14

.gg

-0.14

 Illustrated

-0.14

aked

-0.13

iyon

-0.13

omin

-0.13

POSITIVE LOGITS

 Offer

0.31

 offer

0.29

Offer

0.29

offer

0.28

 present

0.26

 offered

0.24

_offer

0.24

 Offers

0.23

 offers

0.23

present

0.23

Activations Density 0.036%

concepts related to recommendations and evaluations of products or services

No Comments

No Known Activations