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

 whilst

-0.18

 Whilst

-0.18

 connexion

-0.17

 activity

-0.15

 aren

-0.14

achi

-0.14

ÑĤÐ°Ð¿

-0.14

Ãºsqueda

-0.14

 Firstly

-0.14

uant

-0.14

POSITIVE LOGITS

asma

0.15

 pari

0.14

hend

0.14

anje

0.14

abilia

0.14

ç·Ĵ

0.14

rieve

0.14

nj

0.13

/global

0.13

ignon

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.