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

alat

-0.15

oyer

-0.15

RIPT

-0.14

 å¥

-0.14

yna

-0.14

ALAR

-0.14

 Suche

-0.13

iona

-0.13

 Insight

-0.13

pio

-0.13

POSITIVE LOGITS

 personnel

0.14

urai

0.14

 useClass

0.13

erde

0.13

het

0.13

 Melee

0.13

tam

0.13

quine

0.12

zes

0.12

ivor

0.12

Activations Density 0.000%

No Known Activations

This feature has no known activations.