INDEX

Explanations

phrases indicating the concept of extension or prolongation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

erman

-0.16

tower

-0.15

ONY

-0.15

();)

-0.14

adesh

-0.14

mony

-0.14

attach

-0.14

uled

-0.14

axe

-0.14

ye

-0.14

POSITIVE LOGITS

 beyond

0.20

ention

0.18

ibility

0.17

 Beyond

0.17

ential

0.16

.removeAttribute

0.16

(extension

0.16

ive

0.15

ordinary

0.15

sizes

0.15

Activations Density 0.040%

phrases indicating the concept of extension or prolongation

No Comments

No Known Activations