© 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. 11-RESID-POST-AA
    11. 59034
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron flags words associated with legal eligibility or entitlement (e.g. qualify, entitled, appointment, counsel).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hasMany
    -0.06
     konumu
    -0.06
     graphics
    -0.06
    网址
    -0.06
     keyboards
    -0.06
     gripping
    -0.06
     hometown
    -0.06
     metam
    -0.06
    externalActionCode
    -0.06
    ッカー
    -0.06
    POSITIVE LOGITS
    (',')↵
    0.07
    rimon
    0.07
    Includes
    0.06
     منابع
    0.06
     stag
    0.06
     msm
    0.06
     مرتب
    0.06
     CHE
    0.06
    产
    0.06
     onAnimation
    0.06
    Activations Density 0.018%

    No Known Activations