© 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. 23115
    Prev
    Next
    INDEX
    Explanations

    code or logs

    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
     شوند
    -0.07
     ดาว
    -0.06
    وك
    -0.06
    convert
    -0.06
     лютого
    -0.06
    .COL
    -0.06
     Attribution
    -0.06
    nome
    -0.06
     الدولة
    -0.06
     文章
    -0.06
    POSITIVE LOGITS
     stripped
    0.06
    ätz
    0.06
     Rever
    0.06
     garg
    0.06
     γ
    0.06
     potrze
    0.06
     dess
    0.06
    stripe
    0.06
     nur
    0.06
     manifestations
    0.06
    Activations Density 0.029%

    No Known Activations