INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ustria

-0.15

sut

-0.15

utsch

-0.14

osl

-0.14

IPH

-0.14

elere

-0.14

utan

-0.13

OPY

-0.13

allocator

-0.13

POSITIVE LOGITS

 hadn

0.16

 fucked

0.15

fuck

0.15

oleÄį

0.14

åħ

0.14

 cazzo

0.14

 fucks

0.14

 yesterday

0.14

 tonight

0.14

 fuck

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.