INDEX

Explanations

articles that indicate singular or collective concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ummy

-0.14

sson

-0.14

owell

-0.14

-ÑĤÐ°ÐºÐ¸

-0.14

ule

-0.14

 Ð±Ð°Ð½ÐºÑĥ

-0.14

lsi

-0.13

ajs

-0.13

itou

-0.13

isson

-0.13

POSITIVE LOGITS

 feat

0.22

 fact

0.22

.k

0.20

 process

0.19

 factor

0.18

process

0.17

 something

0.17

 which

0.17

 circumstance

0.17

 testament

0.17

Activations Density 0.083%

articles that indicate singular or collective concepts

No Comments

No Known Activations