INDEX

Explanations

phrases related to requests and demands for action or change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

adu

-0.15

ãĥīãĥ«

-0.14

à¸Ķà¸ĩ

-0.14

idon

-0.14

owler

-0.14

&q

-0.13

ersonic

-0.13

gii

-0.13

hlas

-0.13

à¸

-0.13

POSITIVE LOGITS

 thereof

0.35

 doing

0.28

 ello

0.27

 Doing

0.26

Doing

0.25

 bunu

0.25

doing

0.24

 dazu

0.24

 Ø°ÙĦÙĥ

0.22

 accordingly

0.22

Activations Density 0.821%

phrases related to requests and demands for action or change

No Comments

No Known Activations