INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

("//*[@

-0.16

hani

-0.14

icos

-0.14

.Cl

-0.14

linger

-0.14

eteria

-0.14

ictor

-0.14

sha

-0.14

ossal

-0.14

POSITIVE LOGITS

Äı

0.21

_bl

0.18

.metamodel

0.17

bl

0.17

Bl

0.16

Bl

0.16

 Blanch

0.16

 Blind

0.16

bl

0.16

-bl

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.