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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8078
    Prev
    Next
    INDEX
    Explanations

    Keeping up with changes

    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
     designated
    -0.06
     chemical
    -0.06
     cabin
    -0.06
     designate
    -0.06
     laser
    -0.06
    dde
    -0.06
     Stout
    -0.06
    струк
    -0.06
    ствие
    -0.06
     lasers
    -0.06
    POSITIVE LOGITS
    μιλος
    0.08
     obsahuje
    0.07
    .AddColumn
    0.07
    emailer
    0.07
    {}]
    0.07
    自動
    0.07
    ộc
    0.07
     оптим
    0.06
    -border
    0.06
     nộp
    0.06
    Activations Density 0.125%

    No Known Activations