INDEX

Explanations

references to royalty and kings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

vore

-0.15

tml

-0.15

éĩı

-0.15

ngine

-0.15

aken

-0.15

ciÃ³n

-0.14

uple

-0.14

uator

-0.14

adf

-0.14

deki

-0.14

POSITIVE LOGITS

pin

0.21

iol

0.19

innen

0.17

liches

0.16

don

0.16

-of

0.15

fold

0.15

imize

0.15

lake

0.14

esses

0.14

Activations Density 0.093%

references to royalty and kings in various contexts

No Comments

No Known Activations