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

oleon

-0.17

lobs

-0.16

 ngÆ°á»£c

-0.15

langs

-0.15

ooth

-0.14

flix

-0.14

strap

-0.14

 danmark

-0.14

 gonna

-0.14

andas

-0.14

POSITIVE LOGITS

ØŃÙĨ

0.17

 ÙĦÙĥØ±Ø©

0.15

odore

0.14

 McKay

0.14

errick

0.14

 Morr

0.14

ãĤ¤ãĥ³ãĥĪ

0.14

OutOfRangeException

0.14

ince

0.14

TMP

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.