INDEX

Explanations

references to various locations and settings, particularly in promotional or descriptive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

chl

-0.16

prak

-0.15

kest

-0.15

raki

-0.14

 Mate

-0.14

XPath

-0.14

akis

-0.14

ANCELED

-0.13

Ã¡ng

-0.13

awns

-0.13

POSITIVE LOGITS

/on

0.33

/off

0.29

/out

0.28

/at

0.19

/by

0.18

/in

0.17

epad

0.15

/down

0.15

.generated

0.15

aset

0.14

Activations Density 0.042%

references to various locations and settings, particularly in promotional or descriptive contexts

No Comments

No Known Activations