© 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. 19-RESID-POST-AA
    11. 114662
    Prev
    Next
    INDEX
    Explanations

    hundred

    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
    ética
    -0.07
    ….↵↵
    -0.07
     +/-
    -0.07
    앙
    -0.06
    いに
    -0.06
     territorial
    -0.06
     hallmark
    -0.06
     domaine
    -0.06
     pie
    -0.06
     ninete
    -0.06
    POSITIVE LOGITS
    ountains
    0.08
    NTAX
    0.08
    ност
    0.06
     حض
    0.06
    ownt
    0.06
    .radioButton
    0.06
     somewhere
    0.06
    .querySelector
    0.06
    _SYS
    0.06
    _MORE
    0.06
    Activations Density 0.008%

    No Known Activations