INDEX

Explanations

terms that convey a sense of subtlety or gentleness

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

ean

-0.18

@qq

-0.18

nit

-0.16

ãģĤãģĴ

-0.16

redient

-0.15

à¸Ķà¸Ļ

-0.14

orting

-0.14

onical

-0.14

(>

-0.14

ãģĭãĤĭ

-0.14

POSITIVE LOGITS

ewed

0.27

/mod

0.23

yet

0.22

(<

0.22

ãģªãģĮãĤī

0.21

/small

0.21

-medium

0.21

ude

0.20

ly

0.19

ew

0.19

Activations Density 0.098%

terms that convey a sense of subtlety or gentleness

No Comments

No Known Activations