INDEX

Explanations

themes related to differences and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ennen

-0.15

 Magic

-0.14

 MAGIC

-0.14

ÎķÎļ

-0.14

 Romantic

-0.14

agli

-0.14

Bomb

-0.14

Ð¾Ð²ÐµÑĢ

-0.14

TAR

-0.14

rak

-0.14

POSITIVE LOGITS

Pur

0.47

 purge

0.42

pur

0.39

pur

0.38

PUR

0.33

 purification

0.30

PUR

0.29

_PUR

0.26

 purified

0.25

 cleansing

0.20

Activations Density 0.000%

themes related to differences and conflicts

No Comments

No Known Activations