INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

avourites

-0.15

.xz

-0.14

 Haram

-0.14

åģı

-0.14

 Initialise

-0.13

issa

-0.13

 Alman

-0.13

ssa

-0.13

nan

-0.13

 organis

-0.13

POSITIVE LOGITS

uce

0.16

 reck

0.15

its

0.15

—

0.14

 volumes

0.14

 yesterday

0.14

Ne

0.14

 registr

0.14

gfx

0.14

olum

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.