INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Orr

-0.17

iddet

-0.15

ofi

-0.15

 Institutes

-0.14

abus

-0.14

«ĺ

-0.14

Ã©rica

-0.14

ìŀ¡

-0.13

onda

-0.13

cth

-0.13

POSITIVE LOGITS

orado

0.16

elu

0.15

ÐĽÐŀ

0.14

 alright

0.14

faction

0.14

orre

0.14

anford

0.14

agy

0.14

 Borg

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.