INDEX

Explanations

phrases that indicate suitability or inclusivity for a group of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

æ¾

-0.20

lej

-0.19

its

-0.15

ãģ¦

-0.15

ensation

-0.14

Os

-0.14

ampa

-0.14

en

-0.14

ens

-0.14

POSITIVE LOGITS

Å¾ÃŃ

0.16

isphere

0.16

ë§ī

0.15

ATUS

0.15

irit

0.15

>\<^

0.15

 Sesso

0.15

atus

0.15

izon

0.15

Äįka

0.15

Activations Density 0.025%

phrases that indicate suitability or inclusivity for a group of people

No Comments

No Known Activations