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

Geb

-0.14

 Bere

-0.14

usercontent

-0.14

 numel

-0.14

plex

-0.14

FRING

-0.14

atron

-0.13

Ð¼Ñĭ

-0.13

 suits

-0.13

 âĨ

-0.13

POSITIVE LOGITS

Bul

0.23

War

0.19

bul

0.18

 Tweets

0.17

grab

0.16

[.

0.16

 Mosul

0.16

 grasp

0.16

iez

0.15

--

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.