© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125122
    Prev
    Next
    INDEX
    Explanations

    punctuation/structured data

    np_max-act · gemini-2.0-flash

    This neuron fires on list or outline item numbers (e.g. “3.”, “4.”, “5.”, etc.) in structured agendas or enumerations.

    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
    owell
    -0.07
    istes
    -0.06
    Infos
    -0.06
     Hyde
    -0.06
     ελλην
    -0.06
    instagram
    -0.06
     Loving
    -0.06
    ubi
    -0.06
     revolt
    -0.06
    bred
    -0.06
    POSITIVE LOGITS
    =cut
    0.07
    *>::
    0.07
    /T
    0.07
    abcdefghijkl
    0.07
    <typeof
    0.07
     ForCanBeConvertedToForeach
    0.06
    enerima
    0.06
    <Scalar
    0.06
    (base
    0.06
    (AP
    0.06
    Activations Density 0.191%

    No Known Activations