© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 73244
    Prev
    Next
    INDEX
    Explanations

    Reading data files

    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
    _fac
    -0.07
    ='')
    -0.06
     Pentagon
    -0.06
    @store
    -0.06
    ielding
    -0.06
    "...
    -0.06
    >Password
    -0.06
    еф
    -0.06
    emit
    -0.06
    ("<
    -0.06
    POSITIVE LOGITS
    _INCLUDE
    0.07
     lep
    0.07
    /pkg
    0.06
     Ngày
    0.06
    因为
    0.06
     декабря
    0.06
    找
    0.06
     breathable
    0.06
     AppleWebKit
    0.06
     svo
    0.06
    Activations Density 0.009%

    No Known Activations