INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

agit

-0.15

eki

-0.14

 Halk

-0.14

åĦ

-0.14

Fol

-0.14

atan

-0.14

ema

-0.14

 æŀ

-0.14

ne

-0.13

agi

-0.13

POSITIVE LOGITS

 Realty

0.16

 Unters

0.15

æŁĦ

0.14

.FontStyle

0.14

ohana

0.14

 factual

0.14

 Mime

0.13

 Grill

0.13

.jd

0.13

 Negro

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.