INDEX

Explanations

prefixes

np_max-act · gemini-2.0-flash

terms related to medical conditions and therapeutic strategies.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The main thing this neuron does is detect occurrences of words prefixed with “non-” (i.e., the negation prefix “non”).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rahat

-0.07

равиль

-0.07

 parsley

-0.06

htar

-0.06

Mã

-0.06

 itibar

-0.06

，一

-0.06

wang

-0.06

쪽

-0.06

TOR

-0.06

POSITIVE LOGITS

 nonprofit

0.08

 Cooler

0.07

 nonexistent

0.07

cene

0.07

 nonlinear

0.06

 θεω

0.06

 اقتص

0.06

 semif

0.06

 Κο

0.06

ups

0.06

Activations Density 0.059%

prefixes

terms related to medical conditions and therapeutic strategies.

The main thing this neuron does is detect occurrences of words prefixed with “non-” (i.e., the negation prefix “non”).

No Comments

No Known Activations

prefixes

terms related to medical conditions and therapeutic strategies.

The main thing this neuron does is detect occurrences of words prefixed with “non-” (i.e., the negation prefix “non”).

No Comments

No Known Activations