INDEX

Explanations

references to royal titles and their holders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

idores

-0.16

ellen

-0.15

akening

-0.15

abwe

-0.15

Ã¢ng

-0.15

 buurt

-0.14

elu

-0.14

ÐļÐ¢

-0.14

ung

-0.14

asaki

-0.14

POSITIVE LOGITS

sss

0.16

root

0.16

shr

0.15

rut

0.14

essen

0.14

 root

0.14

Î¯Î½Î·

0.14

:eq

0.13

 disap

0.13

Activations Density 0.010%

references to royal titles and their holders

No Comments

No Known Activations