INDEX

Explanations

elements related to numerical data and time stamps

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

 âĢ¦↵

-0.18

 âĢ¦.

-0.16

âĢ¦↵

-0.16

į¼

-0.14

âĢ¦.

-0.14

edit

-0.14

acker

-0.14

âĢ¦

-0.13

 ...)

-0.13

âĢ¦"

-0.13

POSITIVE LOGITS

kaar

0.14

agal

0.14

cela

0.14

suming

0.13

 ***!↵

0.13

 indeb

0.13

EIF

0.13

OLEAN

0.13

YNC

0.13

TestFixture

0.13

Activations Density 0.460%

elements related to numerical data and time stamps

No Comments

No Known Activations