INDEX

Explanations

dates and time-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÑģÐ°Ð¼

-0.15

eni

-0.15

orry

-0.14

inston

-0.14

 touch

-0.14

ambil

-0.14

obo

-0.14

 adulte

-0.14

oplan

-0.13

á»įng

-0.13

POSITIVE LOGITS

 Â·

0.33

Â·

0.28

Â·Â·

0.17

0.16

 ãĥ»

0.16

vida

0.15

ï¿½ï¿½

0.15

pii

0.15

ifes

0.15

 âĢ¢

0.14

Activations Density 0.025%

dates and time-related information

No Comments

No Known Activations