Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 108946
    Prev
    Next
    INDEX
    Explanations

    education degrees

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Points
    -0.07
    .structure
    -0.06
    Measure
    -0.06
    scal
    -0.06
     місця
    -0.06
    _recv
    -0.06
    Fit
    -0.06
    mek
    -0.06
    >e
    -0.06
     Dove
    -0.06
    POSITIVE LOGITS
     prosec
    0.07
     useContext
    0.07
    ForgeryToken
    0.06
     dictionaryWith
    0.06
    SystemService
    0.06
     extremist
    0.06
    -к
    0.06
    ニニ
    0.06
    (compact
    0.06
     Autom
    0.06
    Activations Density 0.022%

    No Known Activations