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

Sel

-0.18

bru

-0.15

Sel

-0.15

 Jays

-0.14

MLS

-0.14

MLS

-0.14

.bb

-0.14

trib

-0.14

inja

-0.14

mlin

-0.14

POSITIVE LOGITS

 counters

0.42

 counter

0.36

 Counter

0.35

-count

0.32

 count

0.32

 Count

0.32

Counter

0.30

-counter

0.30

 COUNT

0.30

counter

0.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.