INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ã³z

-0.15

nder

-0.15

 specially

-0.14

pun

-0.14

é½

-0.14

Prov

-0.14

(*.

-0.14

 desc

-0.14

Ãªs

-0.13

oren

-0.13

POSITIVE LOGITS

åģ

0.15

ellig

0.15

ampa

0.14

Ø·Ø±

0.14

0.13

ilogy

0.13

Ø§ÙħØ¨Ø±

0.13

usra

0.12

uir

0.12

Activations Density 0.000%

No Known Activations

This feature has no known activations.