INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

illes

-0.16

-Mart

-0.14

cis

-0.14

ãģĵãģĿ

-0.14

idade

-0.14

roc

-0.14

Hed

-0.13

vais

-0.13

aries

-0.13

 Ð·Ð°Ð»

-0.13

POSITIVE LOGITS

ensa

0.21

chor

0.17

à¸²à¸¢

0.16

ãģ£ãģ

0.15

dash

0.15

dro

0.15

uali

0.14

Lem

0.14

nea

0.14

/off

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.