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

Ø¶ÙĪ

-0.14

 ÑĥÑģÑĤÑĢÐ°

-0.14

æ

-0.14

-Compatible

-0.13

å±Ĭ

-0.13

.respond

-0.13

ucs

-0.13

-disable

-0.13

ORB

-0.12

irectional

-0.12

POSITIVE LOGITS

 remix

0.23

 FILTER

0.19

 infos

0.19

iginal

0.19

 filters

0.18

 specialised

0.18

 filtering

0.18

 Remix

0.18

 Filtering

0.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.