© 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. 15-RESID-POST-AA
    11. 100709
    Prev
    Next
    INDEX
    Explanations

    Random assortment of text

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Authentic
    -0.07
     orbital
    -0.07
    626
    -0.06
    (so
    -0.06
    _DR
    -0.06
    :])
    -0.06
     absolutely
    -0.06
    оян
    -0.06
    Damage
    -0.06
     hdc
    -0.06
    POSITIVE LOGITS
     functionalities
    0.07
     vài
    0.06
     mělo
    0.06
    .sky
    0.06
    リンク
    0.06
     dalších
    0.06
     Vu
    0.06
     whitespace
    0.06
     jean
    0.06
    (samples
    0.05
    Activations Density 0.000%

    No Known Activations