© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 50033
    Prev
    Next
    INDEX
    Explanations

    Aws

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    итом
    -0.07
    periences
    -0.06
    holiday
    -0.06
     невозможно
    -0.06
    映
    -0.06
    geben
    -0.06
     качества
    -0.06
    npj
    -0.06
     дорог
    -0.06
    působ
    -0.06
    POSITIVE LOGITS
    .prod
    0.07
    _neighbors
    0.07
     kamu
    0.06
    Wins
    0.06
    .Win
    0.06
    prod
    0.06
     prio
    0.06
     Futures
    0.06
    /Sub
    0.06
     уд
    0.06
    Activations Density 0.000%

    No Known Activations