INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

zano

-0.15

INU

-0.15

 submar

-0.15

å©·

-0.14

cela

-0.14

Ð¾Ð¶Ð´ÐµÐ½Ð¸Ðµ

-0.14

 Shade

-0.14

etleri

-0.14

 Hawth

-0.13

quential

-0.13

POSITIVE LOGITS

igos

0.17

 lots

0.15

 Disney

0.15

orney

0.15

èħĲ

0.14

eral

0.14

rov

0.14

 freely

0.14

Ĥ¨

0.14

ente

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.