INDEX

Explanations

references to rowing and related machines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

pany

-0.17

LOT

-0.16

ment

-0.16

 Airlines

-0.16

xit

-0.16

lady

-0.15

lemen

-0.15

CTS

-0.14

ienne

-0.14

POSITIVE LOGITS

/column

0.26

dy

0.21

.Row

0.20

 newRow

0.20

=row

0.20

-cols

0.18

Row

0.17

é©¶

0.17

(row

0.17

enta

0.17

Activations Density 0.030%

references to rowing and related machines

No Comments

No Known Activations