INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ERIC

-0.14

ller

-0.14

ÑĤÐ°Ð»

-0.14

eyh

-0.14

hei

-0.14

aina

-0.14

portun

-0.14

ERC

-0.14

Ä°Z

-0.14

elon

-0.14

POSITIVE LOGITS

hoe

0.16

 Tato

0.16

care

0.15

alia

0.15

burg

0.15

auf

0.15

 affairs

0.15

åº¦

0.14

 Sind

0.14

afe

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.