INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.15

/downloads

-0.14

 complete

-0.14

utherland

-0.14

we

-0.14

 identical

-0.14

inci

-0.14

 required

-0.14

 once

-0.14

 thanks

-0.14

POSITIVE LOGITS

.scalablytyped

0.20

apy

0.18

_mE

0.17

_mD

0.17

_tE

0.17

_Lean

0.16

_Tis

0.16

CLUDING

0.15

_tC

0.15

_tA

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.