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

éĳĳ

-0.16

inqu

-0.14

apos

-0.14

ULA

-0.14

vard

-0.14

ts

-0.14

=img

-0.14

mart

-0.13

tree

-0.13

;++

-0.13

POSITIVE LOGITS

 public

0.19

CAT

0.16

 Public

0.16

/Public

0.16

 PUBLIC

0.15

cat

0.15

bach

0.15

 Cats

0.15

dum

0.15

 private

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.