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

ples

-0.16

esen

-0.15

rve

-0.15

ebek

-0.14

Ð°ÑĢÑħ

-0.14

baum

-0.14

 premi

-0.14

cies

-0.13

elerik

-0.13

essian

-0.13

POSITIVE LOGITS

çºª

0.18

licer

0.17

elli

0.16

 bull

0.16

prof

0.15

olib

0.15

 prof

0.15

 execution

0.15

WX

0.15

 Bull

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.