INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

utton

-0.15

=$('#

-0.14

illa

-0.14

istol

-0.14

 Rouge

-0.13

 genie

-0.13

tv

-0.13

keiten

-0.13

klÃ¤

-0.13

 Levi

-0.13

POSITIVE LOGITS

eprom

0.15

æļ

0.14

furt

0.14

EDGE

0.14

DOMNode

0.13

æĨ

0.13

mlink

0.13

 Halk

0.13

criptor

0.13

Â¤Â¤

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.