INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Untitled

-0.15

.serializer

-0.14

 mand

-0.14

.AWS

-0.13

ags

-0.13

+:

-0.13

ovsky

-0.13

ertino

-0.13

Throws

-0.12

POSITIVE LOGITS

 behaviors

0.15

 kÃ¥

0.15

olean

0.14

=yes

0.14

 Ð·Ð°Ð¿Ð°Ñģ

0.14

iert

0.14

usto

0.13

uyo

0.13

ivist

0.13

lbrace

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.