INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Fucking

-0.17

duk

-0.17

resco

-0.16

SetActive

-0.16

åĬ¿

-0.15

 fucking

-0.14

ingham

-0.14

Ã¡ze

-0.14

thane

-0.14

lie

-0.13

POSITIVE LOGITS

ons

0.18

aa

0.17

aaaa

0.15

unga

0.15

gle

0.15

HS

0.15

lop

0.15

oto

0.15

ee

0.14

iat

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.