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. 19-RESID-POST-AA
    6. 9668
    Prev
    Next
    INDEX
    Explanations

    OR

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Material
    -0.06
     nakne
    -0.06
    _By
    -0.06
    Unchecked
    -0.06
    dıktan
    -0.06
    ]];
    -0.06
    لام
    -0.06
    _IM
    -0.06
     illustr
    -0.06
    ossier
    -0.06
    POSITIVE LOGITS
     <=>
    0.07
     khung
    0.07
     tableView
    0.07
     matrimon
    0.06
    ?:
    0.06
     WT
    0.06
    Music
    0.06
     uni
    0.06
     broccoli
    0.06
     madre
    0.06
    Activations Density 0.001%

    No Known Activations