INDEX

Explanations

names and titles related to individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

pawn

-0.15

 èĬ±

-0.15

imoto

-0.15

searchModel

-0.14

amos

-0.14

Calibri

-0.14

 Vinci

-0.14

ToBounds

-0.14

/Search

-0.13

.Abstractions

-0.13

POSITIVE LOGITS

 Category

0.17

 category

0.17

 Personen

0.16

 categorie

0.16

People

0.16

0.15

_people

0.15

 people

0.15

 cÃ©lib

0.15

people

0.15

Activations Density 0.017%

names and titles related to individuals and organizations

No Comments

No Known Activations