© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 42968
    Prev
    Next
    INDEX
    Explanations

    unauthorized

    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
     xn
    -0.06
     Santa
    -0.06
     Biom
    -0.06
    _Read
    -0.06
    (M
    -0.06
     Κό
    -0.06
    Listen
    -0.06
     cum
    -0.06
     Dul
    -0.06
     Dump
    -0.06
    POSITIVE LOGITS
     unauthorized
    0.17
     Unauthorized
    0.11
    Unauthorized
    0.10
    	↵
    0.07
     toxicity
    0.07
    getStatusCode
    0.07
     vaginal
    0.06
     urgently
    0.06
    viz
    0.06
    TECTED
    0.06
    Activations Density 0.002%

    No Known Activations