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

olv

-0.18

Jad

-0.16

otts

-0.16

jad

-0.15

ean

-0.14

vari

-0.14

ixa

-0.14

toy

-0.14

yan

-0.14

leta

-0.14

POSITIVE LOGITS

stown

0.16

 Canal

0.16

elper

0.15

elman

0.15

/cpp

0.15

udur

0.14

rous

0.14

elsen

0.14

PEND

0.14

DT

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.