INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.ga

-0.14

 Kraj

-0.14

 McDon

-0.13

utdown

-0.13

GRA

-0.13

paque

-0.13

 Jako

-0.13

emma

-0.13

POSITIVE LOGITS

anism

0.17

antino

0.15

 meiden

0.14

inho

0.14

chant

0.14

 eyeb

0.14

Ã¼Ã§

0.14

ess

0.13

 obviously

0.13

ÑĥÐ´Ð¸

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.