INDEX

Explanations

references to the concept of "workplace."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

amet

-0.19

 nackte

-0.17

anced

-0.15

isp

-0.14

apolis

-0.14

amar

-0.14

ham

-0.14

edin

-0.14

-webpack

-0.14

ola

-0.14

POSITIVE LOGITS

 guild

0.14

umo

0.14

iros

0.14

ults

0.13

åĩī

0.13

itemId

0.13

ionate

0.13

udo

0.13

Guild

0.13

ion

0.13

Activations Density 0.003%

references to the concept of "workplace."

No Comments

No Known Activations