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

.enum

-0.15

 Whitney

-0.15

alla

-0.15

plet

-0.15

oze

-0.15

Vals

-0.14

oya

-0.14

remely

-0.14

erule

-0.14

_Anim

-0.14

POSITIVE LOGITS

 (!((

0.15

0.14

0.13

 coco

0.13

ë

0.13

du

0.13

!.↵↵

0.13

dul

0.13

 PROCUREMENT

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.