INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ucci

-0.15

opp

-0.15

etti

-0.14

ibi

-0.14

 ÑģÑĤÐ¾

-0.14

ÅĻe

-0.14

quot

-0.14

 propos

-0.13

iban

-0.13

oux

-0.13

POSITIVE LOGITS

_executor

0.17

enie

0.15

 Default

0.13

 Schro

0.13

andi

0.13

 Discord

0.13

 Peach

0.13

 default

0.13

tero

0.12

exh

0.12

Activations Density 0.000%

No Known Activations

This feature has no known activations.