INDEX

Explanations

words related to the concept of "home" or "place."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

yb

-0.19

ivan

-0.18

edBy

-0.17

elist

-0.17

outh

-0.16

ÏĦÎ¿Î»

-0.15

Ð»ÑĸÐ½Ð½Ñı

-0.15

yw

-0.15

assen

-0.15

POSITIVE LOGITS

yssey

0.33

ding

0.31

ded

0.29

dy

0.26

ders

0.26

der

0.22

den

0.21

ermal

0.21

ges

0.20

nocenÃŃ

0.20

Activations Density 0.038%

words related to the concept of "home" or "place."

No Comments

No Known Activations