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

-0.16

mland

-0.15

emme

-0.15

 Wayback

-0.15

ologne

-0.14

iscard

-0.14

ostel

-0.14

ende

-0.14

inality

-0.14

Son

-0.14

POSITIVE LOGITS

opic

0.15

ohen

0.15

uchi

0.14

_invoke

0.14

odi

0.14

orphic

0.14

esk

0.13

idget

0.13

itsu

0.13

ocup

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.