INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

cept

-0.18

vsp

-0.15

inherits

-0.14

ì±ħ

-0.14

velt

-0.14

ersonic

-0.14

zens

-0.13

enser

-0.13

<<-

-0.13

Å¥

-0.13

POSITIVE LOGITS

etty

0.14

 Rage

0.13

emek

0.13

(*)

0.13

 zeroes

0.13

avez

0.13

alie

0.13

McM

0.13

isse

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.