INDEX

Explanations

references to LGBTQ+ events and pride celebrations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ìģ

-0.14

ritch

-0.14

-0.13

pek

-0.13

avr

-0.13

...

-0.13

 experienced

-0.12

POSITIVE LOGITS

ÑģÐ»Ð¸

0.16

oust

0.14

/crypto

0.14

 ì¦

0.14

ockets

0.14

UIL

0.13

-io

0.13

ModelProperty

0.13

anvas

0.12

otron

0.12

Activations Density 0.366%

references to LGBTQ+ events and pride celebrations

No Comments

No Known Activations