INDEX

Explanations

references to popular trends or cultural phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ç·Ĵ

-0.17

å¼¥

-0.16

 kval

-0.15

çŃĴ

-0.14

gnore

-0.14

.fhir

-0.13

 verdi

-0.13

ÑĢÐ¾Ð·

-0.13

Ø³ØªÙħ

-0.13

estro

-0.13

POSITIVE LOGITS

olia

0.17

 ancient

0.16

 world

0.16

 World

0.16

0.15

 amateur

0.15

 sink

0.15

 footage

0.15

Guy

0.15

 incredible

0.15

Activations Density 0.174%

references to popular trends or cultural phenomena

No Comments

No Known Activations