INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

alfa

-0.19

ãģŁãģı

-0.15

oy

-0.15

ighb

-0.15

vs

-0.14

uggest

-0.14

 hello

-0.13

 compliments

-0.13

ume

-0.13

ourage

-0.13

POSITIVE LOGITS

ffen

0.15

IMO

0.15

icine

0.15

ller

0.14

ikut

0.14

those

0.14

cen

0.13

 Dich

0.13

_PTR

0.13

Those

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.