INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

rous

-0.19

emme

-0.15

ako

-0.15

@js

-0.15

cil

-0.15

ahoma

-0.15

 Ulus

-0.14

amins

-0.14

azers

-0.14

EMPLARY

-0.14

POSITIVE LOGITS

ets

0.17

0.15

xdc

0.15

 followed

0.15

Sm

0.14

imit

0.14

 Bernstein

0.14

 Williamson

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.