INDEX

Explanations

references to personal information and its implications in security contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 REALLY

-0.23

 biraz

-0.22

 trochu

-0.20

 somewhat

-0.19

 Ð½ÐµÐ¼Ð½Ð¾Ð³Ð¾

-0.19

æľīçĤ¹

-0.17

 SOME

-0.17

 Hopefully

-0.16

 maybe

-0.16

 perhaps

-0.16

POSITIVE LOGITS

 absolutely

0.36

 exactly

0.31

 literally

0.30

 precisely

0.30

 completely

0.29

 perfectly

0.29

 Absolutely

0.24

 entirely

0.24

 totally

0.23

 actually

0.23

Activations Density 1.087%

references to personal information and its implications in security contexts

No Comments

No Known Activations