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

ă

-0.15

à¥Ľ

-0.15

à¸·à¸Ńà¸ĸ

-0.14

fty

-0.14

usto

-0.14

EV

-0.13

 succes

-0.13

agine

-0.13

Ä±rak

-0.13

sembled

-0.13

POSITIVE LOGITS

kee

0.14

poi

0.14

MOTE

0.14

cee

0.14

apid

0.13

 Ãºlt

0.13

ikh

0.13

Ð¾ÐºÐµ

0.13

_acquire

0.13

uelle

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.