© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 106764
    Prev
    Next
    INDEX
    Explanations

    software 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_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
    .entities
    -0.07
    >>();↵
    -0.06
     ships
    -0.06
     FK
    -0.06
     folders
    -0.06
     Lep
    -0.05
     annonces
    -0.05
     Apartments
    -0.05
    旅
    -0.05
    =datetime
    -0.05
    POSITIVE LOGITS
    loha
    0.08
     (?
    0.08
     ninete
    0.07
    .NewGuid
    0.07
     DRIVER
    0.07
    णन
    0.07
    �재
    0.06
    ≦
    0.06
    Colour
    0.06
    URRE
    0.06
    Activations Density 0.000%

    No Known Activations