INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

è¦ª

-0.15

BE

-0.15

lien

-0.14

_beg

-0.14

 Misc

-0.14

fu

-0.14

:///

-0.14

Ĺ

-0.14

clide

-0.14

POSITIVE LOGITS

.Library

0.16

ãĥĥãĥĹ

0.15

 Barcl

0.15

Jvm

0.14

 brains

0.14

embro

0.14

ngr

0.14

 Zucker

0.14

meer

0.14

_warning

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.