INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

unders

-0.17

APH

-0.16

ãĤ¦ãĤ¹

-0.16

itten

-0.16

.Syntax

-0.15

eric

-0.15

ãĥ«ãĥī

-0.15

fus

-0.14

oblins

-0.14

Fus

-0.14

POSITIVE LOGITS

ensi

0.17

Eh

0.15

 Gent

0.15

Zwe

0.14

 Lair

0.14

 gent

0.14

ucht

0.14

rawer

0.14

Wit

0.14

ilyn

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.