INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

rawler

-0.15

 kÃ¥

-0.15

åįĵ

-0.14

aghan

-0.14

iko

-0.14

ÄŁen

-0.14

 Giuliani

-0.14

 dispatch

-0.14

ÑĸÐ»ÑĮÑĪ

-0.14

 Rudy

-0.14

POSITIVE LOGITS

anel

0.18

aravel

0.14

ycz

0.14

essenger

0.14

 ever

0.14

asn

0.14

ÐĲÑĢÑħÑĸÐ²

0.14

Amb

0.14

GREE

0.14

anza

0.13

Activations Density 0.062%

No Comments

No Known Activations