INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

agine

-0.16

ÑĢÐ¾Ð¹

-0.14

registr

-0.13

.constraint

-0.13

nil

-0.13

Î¬Î½Ïī

-0.13

ieee

-0.13

pas

-0.13

fel

-0.13

icensing

-0.12

POSITIVE LOGITS

.ReadAll

0.16

adio

0.15

Normalize

0.15

iffin

0.15

uzzer

0.15

ãĥĩãĥ«

0.14

(Global

0.14

ä¹ĭ

0.14

ÏģÎµÏĤ

0.14

.mapbox

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.