INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ordo

-0.14

ooth

-0.14

æĽľ

-0.13

 Safe

-0.13

 themselves

-0.13

ront

-0.13

Wak

-0.13

Safe

-0.13

avid

-0.13

udio

-0.13

POSITIVE LOGITS

Assign

0.15

assignments

0.15

though

0.15

mnop

0.15

 Assign

0.15

 though

0.14

_assign

0.14

 Jako

0.14

 MOUSE

0.14

ispiel

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.