INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.15

.ci

-0.15

OUNTER

-0.14

eliness

-0.14

('

-0.14

wers

-0.13

 Brain

-0.13

/--

-0.13

ă

-0.13

POSITIVE LOGITS

Pad

0.22

Pad

0.18

pad

0.18

pad

0.16

epad

0.15

_pad

0.15

IFA

0.15

esch

0.14

PAD

0.14

 Padres

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.