INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 toler

-0.15

lac

-0.15

ocz

-0.15

ellen

-0.14

ieee

-0.14

 connexion

-0.14

 Roll

-0.14

eware

-0.14

-0.13

POSITIVE LOGITS

ocha

0.15

íĪ¬

0.14

 Ø£ÙħØ§

0.14

ìĤ°

0.14

agma

0.14

Å¼e

0.14

Meteor

0.13

muz

0.13

-prepend

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.