© 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 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. 7-RESID-POST-AA
    11. 29142
    Prev
    Next
    INDEX
    Explanations

    rotational

    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
    _idxs
    -0.07
     نشان
    -0.06
     زد
    -0.06
     XmlNode
    -0.06
     نشده
    -0.06
    roupe
    -0.06
     paranoia
    -0.06
    たら
    -0.06
    Orange
    -0.06
     PF
    -0.06
    POSITIVE LOGITS
     qualification
    0.08
     Lift
    0.07
    roperty
    0.07
    Expense
    0.07
     Excellence
    0.06
     الغ
    0.06
    _CERT
    0.06
    /Getty
    0.06
    etí
    0.06
     Cry
    0.06
    Activations Density 0.007%

    No Known Activations