INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 believed

-0.15

 Intr

-0.14

dok

-0.14

 Proud

-0.14

 reass

-0.13

 mÃ¼k

-0.13

_EXPECT

-0.13

 fond

-0.13

PCODE

-0.13

POSITIVE LOGITS

jih

0.15

ignon

0.15

icari

0.14

å¯¸

0.14

 Brexit

0.14

regnum

0.14

itura

0.14

andum

0.14

0.13

erli

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.