INDEX

Explanations

terms related to linear equations and relationships

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

amax

-0.20

amac

-0.15

Ð»Ð¸Ð²

-0.15

engers

-0.14

esen

-0.14

ek

-0.14

Ð½Ð¸ÑĩÐµÑģ

-0.14

_UNUSED

-0.13

alist

-0.13

tega

-0.13

POSITIVE LOGITS

ized

0.26

ly

0.23

izable

0.22

izing

0.22

ities

0.21

ization

0.20

-linear

0.20

ize

0.18

/qu

0.17

ised

0.16

Activations Density 0.021%

terms related to linear equations and relationships

No Comments

No Known Activations