INDEX

Explanations

allergic reactions

np_max-act · gemini-2.0-flash

This neuron activates on parts of words related to severe allergic reactions (e.g. “anaphylactic,” “anaphylaxis”) and their treatment (“epinephrine”).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

аг

-0.07

_MAXIMUM

-0.07

ió

-0.06

 TextView

-0.06

 adjacency

-0.06

 editors

-0.06

فن

-0.06

-handler

-0.06

�

-0.06

ords

-0.06

POSITIVE LOGITS

rf

0.06

Calc

0.06

 quarterback

0.06

 muscular

0.06

 respondent

0.06

 frowned

0.06

Pur

0.06

 polygon

0.06

лет

0.06

 Fame

0.06

Activations Density 0.002%

allergic reactions

This neuron activates on parts of words related to severe allergic reactions (e.g. “anaphylactic,” “anaphylaxis”) and their treatment (“epinephrine”).

No Comments

No Known Activations