INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

bout

-0.17

 precedent

-0.15

rocket

-0.15

Ã³ng

-0.14

ourt

-0.14

 Lakes

-0.14

ros

-0.14

oliday

-0.14

xFFF

-0.14

ELLOW

-0.13

POSITIVE LOGITS

 universe

0.19

 environment

0.19

 approach

0.17

 portion

0.17

 framework

0.16

apo

0.16

 hierarchy

0.16

iphery

0.15

 regime

0.15

iverse

0.15

Activations Density 0.031%

No Comments

No Known Activations