© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23-RESID-POST-AA
    11. 63122
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canadian
    -0.06
     případech
    -0.06
     puedo
    -0.06
    ureau
    -0.06
    ases
    -0.06
    едагог
    -0.06
    Tcp
    -0.06
    ASE
    -0.06
    ase
    -0.06
     mercado
    -0.06
    POSITIVE LOGITS
    )":
    0.07
     العظ
    0.07
     submit
    0.07
     نفت
    0.06
     counted
    0.06
    ังไม
    0.06
     tỷ
    0.06
    tolua
    0.06
    MARY
    0.06
    (SIG
    0.06
    Activations Density 0.025%

    No Known Activations