© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 39356
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    -step
    -0.07
     Rever
    -0.06
    -road
    -0.06
     subrange
    -0.06
    SENS
    -0.06
     своей
    -0.06
    EO
    -0.06
     decks
    -0.06
     dua
    -0.06
     Genome
    -0.06
    POSITIVE LOGITS
     Retorna
    0.07
     informal
    0.07
    เทคโนโลย
    0.06
     삼성
    0.06
    _pdata
    0.06
    平成
    0.06
     impedance
    0.06
     QByteArray
    0.06
     er
    0.06
    ickle
    0.06
    Activations Density 0.115%

    No Known Activations