INDEX

Explanations

references to geographic locations and governmental activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 undo

-0.16

 Pont

-0.15

 Huffman

-0.15

SAF

-0.15

 undone

-0.14

 Haskell

-0.14

amax

-0.14

instein

-0.14

ä¼ĳ

-0.14

Pont

-0.14

POSITIVE LOGITS

Cay

0.42

Bod

0.21

 Turks

0.20

UDP

0.18

rollo

0.18

CNS

0.17

 Sting

0.17

bod

0.17

>}</

0.16

aign

0.16

Activations Density 0.002%

references to geographic locations and governmental activities

No Comments

No Known Activations