INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

egra

-0.14

-esque

-0.14

ÑıÑĩ

-0.14

GetObject

-0.14

pawn

-0.14

ÏħÏĦÏĮ

-0.13

Misc

-0.13

&quot

-0.13

adas

-0.13

&gt

-0.13

POSITIVE LOGITS

ColumnInfo

0.15

vents

0.14

QRS

0.14

uncture

0.14

ourage

0.14

 ä¸

0.13

("$.

0.13

æµ©

0.13

edio

0.13

Ø£

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.