INDEX

Explanations

references to organizational names and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

igest

-0.16

-0.15

loi

-0.15

ewe

-0.15

mart

-0.14

arro

-0.14

chein

-0.14

 LOVE

-0.14

 bank

-0.13

.Mar

-0.13

POSITIVE LOGITS

 Affero

0.17

.gnu

0.17

.tex

0.17

gratis

0.16

 Free

0.16

 Wahl

0.16

ottle

0.15

Freedom

0.15

 Hayden

0.15

Free

0.15

Activations Density 0.008%

references to organizational names and addresses

No Comments

No Known Activations