INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.19

 Bless

-0.15

Ã¤Ã¤n

-0.15

ansi

-0.14

escal

-0.14

ters

-0.14

hel

-0.14

 Trouble

-0.13

adle

-0.13

 nearest

-0.13

POSITIVE LOGITS

 Sesso

0.18

ÏĦÎ¹Îº

0.15

 ÑĢÐ°Ð·Ð¼

0.14

oppins

0.14

ofday

0.14

å¾Ħ

0.14

otron

0.14

.Alignment

0.14

illez

0.14

ìĬ´

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.