© 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. 91681
    Prev
    Next
    INDEX
    Explanations

    things people want

    np_max-act · gemini-2.0-flash

    The neuron fires on marketing-style future predictions about user adoption or appeal—phrases like “people will use,” “customers will love,” “readers would love,” etc.

    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
     improperly
    -0.06
    جو
    -0.06
    istes
    -0.06
    odos
    -0.06
    الی
    -0.06
    _sessions
    -0.06
     incorrectly
    -0.06
     Kaf
    -0.06
    주는
    -0.06
    ال
    -0.06
    POSITIVE LOGITS
     "__
    0.07
     frække
    0.07
    .netflix
    0.07
     Cooperation
    0.07
     leo
    0.07
     �
    0.06
    _git
    0.06
     giành
    0.06
    字段
    0.06
     preaching
    0.06
    Activations Density 0.038%

    No Known Activations