INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

urtle

-0.15

-0.14

 authorized

-0.14

igo

-0.14

ahan

-0.14

 stabilized

-0.13

POSITIVE LOGITS

rych

0.15

ainter

0.15

adm

0.15

ÑĥÑģ

0.15

_TP

0.15

elib

0.14

-eslint

0.14

 chaud

0.13

enberg

0.13

eprom

0.13

Activations Density 0.033%

No Comments

No Known Activations