INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

inn

-0.16

ichtig

-0.14

inem

-0.14

inta

-0.14

 Albert

-0.13

 Naturally

-0.13

onso

-0.13

asan

-0.13

<>

-0.13

POSITIVE LOGITS

ÙĪÙī

0.15

¦¬

0.14

ployment

0.14

ICLE

0.14

errs

0.13

leep

0.13

.exclude

0.13

-scrollbar

0.13

omens

0.13

acement

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.