INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 gimm

-0.14

noch

-0.14

 Lamar

-0.14

ÅĦ

-0.13

ackets

-0.13

AES

-0.13

.bz

-0.13

unwrap

-0.13

alth

-0.13

ime

-0.13

POSITIVE LOGITS

 delightful

0.17

raÅ¾

0.16

 Australians

0.15

 funnel

0.15

 like

0.14

erb

0.14

 Canberra

0.14

 lovely

0.14

 awesome

0.14

 hilarious

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.