INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

intage

-0.15

xBD

-0.15

$lang

-0.14

 Shoe

-0.14

earn

-0.14

 mate

-0.14

 blink

-0.13

stitution

-0.13

GAN

-0.13

 span

-0.13

POSITIVE LOGITS

_simulation

0.21

SIM

0.21

 simulation

0.21

SIM

0.20

simulation

0.19

 simulations

0.19

 Simulation

0.18

-stage

0.17

Simulation

0.17

 sims

0.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.