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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 18729
    Prev
    Next
    INDEX
    Explanations

    some/my/your

    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
     surgeons
    -0.06
    \helpers
    -0.06
    sı
    -0.06
    hesion
    -0.06
    uyến
    -0.06
    activation
    -0.06
    _indices
    -0.06
    meler
    -0.06
    	restore
    -0.06
    認
    -0.05
    POSITIVE LOGITS
    ibal
    0.07
     stays
    0.07
     eliminar
    0.07
    При
    0.06
    ony
    0.06
     '-';↵
    0.06
     درون
    0.06
     Television
    0.06
     legacy
    0.06
    _picture
    0.06
    Activations Density 0.046%

    No Known Activations