INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ð¸ÑĤÐ¾Ð¼

-0.20

åĵª

-0.15

 konkrÃ©t

-0.15

mos

-0.14

urgeon

-0.14

.hw

-0.14

å±±å¸Ĥ

-0.14

Ã¶ren

-0.13

erson

-0.13

imon

-0.13

POSITIVE LOGITS

inka

0.17

ãĥ³ãĤ°ãĥ«

0.16

ìĪľ

0.15

 åĺ

0.14

 ones

0.14

-theme

0.14

atel

0.13

 onwards

0.13

ija

0.13

FFFF

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.