INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

etas

-0.16

PCODE

-0.15

á»Ľp

-0.14

gli

-0.14

 Centers

-0.14

roe

-0.14

èģ²

-0.14

 Volk

-0.14

å£°

-0.13

POSITIVE LOGITS

ocus

0.15

osed

0.15

·æĸ°

0.15

isis

0.14

ict

0.14

andum

0.14

 Doing

0.14

odo

0.14

otos

0.14

agenda

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.