INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

.rules

-0.17

esis

-0.17

eldorf

-0.16

 Shib

-0.15

ocide

-0.15

elves

-0.15

.calls

-0.15

Ascii

-0.15

æŃ¢

-0.14

ehr

-0.14

POSITIVE LOGITS

ori

0.14

oot

0.14

vit

0.14

_scenario

0.14

 DropIndex

0.14

URT

0.13

Ð¾Ð¾Ð±ÑĢÐ°Ð·

0.13

voy

0.13

bor

0.13

exc

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.