INDEX

Explanations

references to historical years, particularly those in the 1800s

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

bject

-0.17

YRO

-0.15

ãĤ¸ãĤ¢

-0.14

phis

-0.14

isi

-0.14

CJK

-0.14

assi

-0.14

inese

-0.14

bla

-0.14

eph

-0.14

POSITIVE LOGITS

bjerg

0.16

sed

0.15

agg

0.15

orus

0.15

lak

0.15

ubble

0.14

åĿĬ

0.14

rina

0.14

 Piper

0.14

Activations Density 0.008%

references to historical years, particularly those in the 1800s

No Comments

No Known Activations