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

eph

-0.18

akter

-0.14

ika

-0.14

eza

-0.14

ington

-0.14

å¸Ī

-0.14

Ø±Ø§Ø¯

-0.14

iston

-0.13

vala

-0.13

DataAdapter

-0.13

POSITIVE LOGITS

adin

0.15

ç«ľ

0.15

ofil

0.14

 Sweat

0.14

lane

0.14

achs

0.14

éŀ

0.14

sal

0.14

Ð°ÑĤÐ¾Ð²

0.14

Sal

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.