© 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. 11-RESID-POST-AA
    6. 27403
    Prev
    Next
    INDEX
    Explanations

    Beat

    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
    GLIGENCE
    -0.07
     arou
    -0.07
     aunque
    -0.07
     quelle
    -0.06
     quel
    -0.06
    /legal
    -0.06
    dition
    -0.06
     nuru
    -0.06
     beste
    -0.06
    яем
    -0.06
    POSITIVE LOGITS
     Somerset
    0.07
    )),↵
    0.06
     хозяй
    0.06
    /vue
    0.06
    (tr
    0.06
    ('./
    0.06
    _DBG
    0.06
    Rotor
    0.06
    ------------↵
    0.06
     Анг
    0.06
    Activations Density 0.051%

    No Known Activations