INDEX

Explanations

references to control systems and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

hood

-0.22

elves

-0.16

alborg

-0.15

icals

-0.14

eward

-0.14

idUser

-0.14

redicate

-0.14

ibaba

-0.14

Åº

-0.14

iatrics

-0.14

POSITIVE LOGITS

led

0.20

/control

0.19

ted

0.19

ateral

0.19

ship

0.18

ters

0.18

ador

0.17

-Control

0.16

lix

0.15

/manage

0.15

Activations Density 0.039%

references to control systems and their components

No Comments

No Known Activations