Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 122124
    Prev
    Next
    INDEX
    Explanations

    othermal

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сен
    -0.07
    Ed
    -0.07
    [parent
    -0.07
    現在
    -0.07
    З
    -0.07
    fila
    -0.06
     Delaware
    -0.06
     ape
    -0.06
     aun
    -0.06
     Truck
    -0.06
    POSITIVE LOGITS
    /use
    0.06
    	number
    0.06
     mutlak
    0.06
     Euras
    0.06
     fallout
    0.06
    .');
    0.06
    .asset
    0.06
     foto
    0.06
    _UINT
    0.06
    heiro
    0.06
    Activations Density 0.003%

    No Known Activations