INDEX

Explanations

phrases indicating academic titles or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

indow

-0.18

_ACL

-0.17

itÃ©

-0.16

abis

-0.15

rowsable

-0.15

ingly

-0.15

uments

-0.14

ipse

-0.14

roscope

-0.14

iÄĩ

-0.14

POSITIVE LOGITS

riz

0.16

anch

0.16

0.15

locker

0.14

prite

0.14

izzo

0.14

ansom

0.14

yah

0.14

idis

0.13

CellStyle

0.13

Activations Density 0.004%

phrases indicating academic titles or positions

No Comments

No Known Activations