INDEX

Explanations

phrases related to eliminating unwanted elements or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ces

-0.18

ection

-0.18

odule

-0.15

ãģĭãĤı

-0.15

unny

-0.15

edis

-0.15

otas

-0.15

Ã¡ÅĻ

-0.15

ãĥķãĤ

-0.14

ç»§

-0.14

POSITIVE LOGITS

yne

0.16

 gross

0.15

 roli

0.14

 treat

0.14

 Pause

0.14

ãģªãģĬ

0.14

 treated

0.13

ex

0.13

icare

0.13

 Treat

0.13

Activations Density 0.008%

phrases related to eliminating unwanted elements or conditions

No Comments

No Known Activations