INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

eger

-0.15

 Lauderdale

-0.15

EditMode

-0.14

 federally

-0.14

ģn

-0.14

 Baum

-0.14

 Fell

-0.14

rok

-0.13

igit

-0.13

issor

-0.13

POSITIVE LOGITS

 catalog

0.17

iben

0.17

Catalog

0.17

dzi

0.16

catalog

0.16

_catalog

0.15

 Catalog

0.15

 catalogue

0.15

nez

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.