INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

çĶ

-0.17

CommandEvent

-0.16

ibase

-0.16

rips

-0.15

atz

-0.15

comed

-0.14

anan

-0.14

ospel

-0.14

WithOptions

-0.14

uang

-0.14

POSITIVE LOGITS

 motions

0.16

acular

0.15

MISSION

0.14

yms

0.14

iders

0.14

assi

0.13

 resign

0.13

bras

0.13

 steam

0.13

ddy

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.