INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ucci

-0.17

lut

-0.16

 âĢ¦

-0.15

 seasons

-0.15

combe

-0.14

 ðŁ

-0.14

mitt

-0.14

 penc

-0.14

 Season

-0.14

Aug

-0.14

POSITIVE LOGITS

ÐµÑģÑĤÐ¾

0.18

lue

0.14

é§

0.14

åĽ³

0.14

-Jun

0.14

rÃ³d

0.14

orado

0.13

andelier

0.13

Ð¶ÐµÐ½ÑĮ

0.13

uten

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.