INDEX

Explanations

instances of the term "use" alongside references to programming languages or technical concepts

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

ooks

-0.19

ova

-0.18

ofs

-0.17

ional

-0.16

LB

-0.16

pressed

-0.16

ubber

-0.16

ergency

-0.14

cret

-0.14

inky

-0.14

POSITIVE LOGITS

sville

0.18

alic

0.17

aint

0.17

ëĭī

0.16

æİ

0.16

ibernate

0.14

ivol

0.14

_common

0.14

lessness

0.14

 Levine

0.14

Activations Density 0.008%

instances of the term "use" alongside references to programming languages or technical concepts

No Comments

No Known Activations