INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uro

-0.14

iw

-0.14

ipo

-0.14

ken

-0.14

floor

-0.14

ffects

-0.14

essional

-0.13

wich

-0.13

 floor

-0.13

Pow

-0.13

POSITIVE LOGITS

 principle

0.25

 practice

0.21

 presence

0.20

 contrast

0.19

 contrad

0.18

practice

0.18

 spirit

0.17

 analogy

0.17

presence

0.17

 absence

0.17

Activations Density 0.068%

No Comments

No Known Activations