INDEX

Explanations

phrases indicating possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 underwent

-0.17

onth

-0.16

nika

-0.14

adel

-0.14

ies

-0.14

 experimentation

-0.14

edl

-0.13

 ÄĳÃ£

-0.13

ific

-0.13

POSITIVE LOGITS

 been

0.29

nt

0.22

htag

0.20

/is

0.19

been

0.19

 become

0.19

 Been

0.19

/w

0.18

 sido

0.18

 thá»ĥ

0.17

Activations Density 0.567%

phrases indicating possession or ownership

No Comments

No Known Activations