INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ãģ£ãģ±ãģĦ

-0.16

omba

-0.15

herits

-0.15

iddi

-0.15

itesse

-0.15

unma

-0.14

 cudaMemcpy

-0.14

HeaderCode

-0.14

.Cmd

-0.14

POSITIVE LOGITS

0.15

 anybody

0.15

 à¹Ĩ

0.15

 Kear

0.14

eno

0.14

 Neighbor

0.14

thing

0.13

ichi

0.13

 Hardy

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.