© 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. 19-RESID-POST-AA
    6. 118226
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _p
    -0.06
    _geo
    -0.06
     Dylan
    -0.06
     feats
    -0.06
     anál
    -0.06
    DataContext
    -0.06
    _widget
    -0.06
    lığa
    -0.06
    적
    -0.06
     votre
    -0.06
    POSITIVE LOGITS
     kontakt
    0.07
    generic
    0.07
     menacing
    0.07
     Katrina
    0.06
     IDEOGRAPH
    0.06
     annonces
    0.06
     clientId
    0.06
    :::/
    0.06
    .Scan
    0.06
     трохи
    0.06
    Activations Density 0.247%

    No Known Activations