© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126315
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron detects phrases indicating that something is used “alone,” “in,” or “in combination,” i.e. constructions specifying whether an element stands by itself or together with another.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    近
    -0.07
     використовувати
    -0.06
     theology
    -0.06
     buiten
    -0.06
     sharedApplication
    -0.06
     giấy
    -0.06
    DataProvider
    -0.05
     світу
    -0.05
     franç
    -0.05
    sure
    -0.05
    POSITIVE LOGITS
    .sz
    0.07
     synaptic
    0.07
    مر
    0.07
    pron
    0.07
    ='-
    0.07
     aşam
    0.07
     smaller
    0.07
     synchronous
    0.07
     ：
    0.07
    оказ
    0.07
    Activations Density 0.010%

    No Known Activations