INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

venta

-0.15

.icons

-0.15

reffen

-0.14

orra

-0.14

.FALSE

-0.14

olem

-0.14

erra

-0.14

ota

-0.14

eral

-0.14

icons

-0.14

POSITIVE LOGITS

 Trace

0.14

AIM

0.14

 Ease

0.14

 Times

0.14

kehr

0.14

LIC

0.13

 Lima

0.13

rock

0.13

-tip

0.13

Ukr

0.13

Activations Density 0.003%

No Comments

No Known Activations