INDEX

Explanations

phrases related to assistance and support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

to

-0.25

 Äĳá»ĥ

-0.18

sto

-0.15

/UI

-0.15

atts

-0.15

 alot

-0.15

ToLeft

-0.14

ToEnd

-0.14

to

-0.14

ises

-0.14

POSITIVE LOGITS

 purposes

0.21

ify

0.20

/manage

0.19

 further

0.18

/disable

0.18

/remove

0.18

 desired

0.17

/save

0.17

/update

0.17

itate

0.15

Activations Density 0.829%

phrases related to assistance and support

No Comments

No Known Activations