INDEX

Explanations

key concepts and ideas related to anonymity and contextual factors in various domains

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

ICI

-0.17

alse

-0.16

-0.15

.Apis

-0.14

Mappings

-0.14

uling

-0.14

 quoi

-0.14

uffles

-0.14

 Rossi

-0.13

mrt

-0.13

POSITIVE LOGITS

 role

0.28

 roles

0.20

 impact

0.19

 relationship

0.19

 reasons

0.19

role

0.18

 ways

0.18

 Role

0.18

Role

0.18

 importance

0.18

Activations Density 0.130%

key concepts and ideas related to anonymity and contextual factors in various domains

No Comments

No Known Activations