INDEX

Explanations

terms or symbols typically associated with ratings or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

...↵↵

-0.16

 BuzzFeed

-0.16

...

-0.16

...(

-0.16

isci

-0.15

...↵

-0.15

ðŁ

-0.15

..."↵↵

-0.14

ertz

-0.14

Ã¸j

-0.14

POSITIVE LOGITS

 solutions

0.19

 representing

0.18

 Solutions

0.17

 representation

0.17

 representative

0.16

_US

0.16

 solving

0.16

represent

0.15

 represent

0.15

 Represent

0.15

Activations Density 0.003%

terms or symbols typically associated with ratings or evaluations

No Comments

No Known Activations