INDEX

Explanations

positive transformations or improvements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Cla

-0.15

bud

-0.14

uplicate

-0.14

 label

-0.14

ernen

-0.14

inker

-0.14

 Shooter

-0.14

 è¦

-0.13

iyel

-0.13

POSITIVE LOGITS

idth

0.18

athom

0.16

anou

0.15

-properties

0.15

icks

0.15

alon

0.15

opis

0.15

oui

0.15

 Harper

0.14

amet

0.14

Activations Density 0.191%

positive transformations or improvements in various contexts

No Comments

No Known Activations