© 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. 15-RESID-POST-AA
    11. 128174
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
     lids
    -0.07
     detailed
    -0.07
     Vanguard
    -0.07
     amazing
    -0.07
    脸
    -0.07
    來
    -0.06
     bos
    -0.06
    ats
    -0.06
     relieved
    -0.06
     lud
    -0.06
    POSITIVE LOGITS
     reinst
    0.07
     uniq
    0.07
    _compute
    0.06
     również
    0.06
    (hw
    0.06
    bble
    0.06
    roe
    0.06
    ationale
    0.06
     skvěl
    0.06
    ORIZATION
    0.06
    Activations Density 0.242%

    No Known Activations