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

ylvania

-0.16

bus

-0.16

ÑģÑĤÐ¸

-0.14

azzo

-0.14

busters

-0.14

 Franco

-0.14

ewing

-0.14

éĻµ

-0.14

bose

-0.14

raction

-0.14

POSITIVE LOGITS

edl

0.16

ighth

0.15

edn

0.14

ordin

0.14

ãģŃ

0.14

oran

0.14

DataType

0.14

SEQ

0.14

ï¼¡

0.13

HRESULT

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.