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

apel

-0.15

 Ø´ÙĪ

-0.15

iov

-0.15

Tiles

-0.14

çľ¼çĿĽ

-0.14

eration

-0.14

enty

-0.14

_singular

-0.14

 Link

-0.13

POSITIVE LOGITS

ulla

0.16

CX

0.15

.getDescription

0.15

riot

0.15

oulder

0.15

illis

0.15

INF

0.14

lider

0.14

 Stamp

0.14

uis

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.