© 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. 7-RESID-POST-AA
    11. 118993
    Prev
    Next
    INDEX
    Explanations

    lists and examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAndFeel
    -0.07
    отов
    -0.06
     dbName
    -0.06
     TypeName
    -0.06
     dto
    -0.06
    .DropDownItems
    -0.06
    الك
    -0.06
    苗
    -0.06
    .intent
    -0.06
    ่วย
    -0.06
    POSITIVE LOGITS
    _u
    0.07
    .ret
    0.07
     SEQ
    0.07
     variance
    0.06
     conclude
    0.06
    :no
    0.06
     bounced
    0.06
     Dark
    0.06
     Kad
    0.06
    ео
    0.06
    Activations Density 0.350%

    No Known Activations