INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

@$_

-0.15

 kÃ¬

-0.14

rh

-0.13

 blunt

-0.13

eah

-0.13

 Piano

-0.13

 getch

-0.13

 voks

-0.13

via

-0.13

POSITIVE LOGITS

 stylist

0.17

tent

0.17

å°ļ

0.14

strcasecmp

0.14

sched

0.14

Ð¾Ð´Ð°

0.13

.twitch

0.13

 intermedi

0.13

overall

0.13

.documentation

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.