INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

marsh

-0.15

azz

-0.15

ç§

-0.14

lama

-0.14

andon

-0.14

 discipline

-0.14

Dre

-0.14

obo

-0.14

POSITIVE LOGITS

ÑĥÑģÑĤ

0.18

 Eaton

0.15

 Orig

0.14

ilers

0.14

 plÃ¡

0.14

datal

0.14

liÅ¡

0.14

yte

0.14

yd

0.14

ÐłÐĺ

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.