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

ospace

-0.15

@admin

-0.15

-0.14

—

-0.14

zik

-0.14

Migration

-0.14

imity

-0.14

quot

-0.14

sik

-0.13

_DLL

-0.13

POSITIVE LOGITS

 external

0.16

 proxies

0.15

 outer

0.15

 Outer

0.14

 masculine

0.14

external

0.14

 External

0.14

 repression

0.14

 Client

0.13

 stockholm

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.