INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.16

lor

-0.15

.Emit

-0.14

inh

-0.14

UILD

-0.14

laden

-0.14

elas

-0.14

Sap

-0.14

rid

-0.14

iane

-0.14

POSITIVE LOGITS

rock

0.17

å°ĸ

0.16

ettle

0.16

ownik

0.15

antis

0.14

mdl

0.14

wi

0.14

 Triangle

0.13

ummings

0.13

à¹Ħà¸Ĥ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.