© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 84698
    Prev
    Next
    INDEX
    Explanations

    (

    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
     Samantha
    -0.07
     manufactures
    -0.07
     ausp
    -0.07
    (bar
    -0.07
    kd
    -0.07
     luder
    -0.06
    寫
    -0.06
     anx
    -0.06
    includes
    -0.06
    DataMember
    -0.06
    POSITIVE LOGITS
     Кор
    0.07
    ไฟฟ
    0.06
    lossen
    0.06
    _sess
    0.06
    modo
    0.06
     exclusive
    0.06
     Mädchen
    0.06
     carrera
    0.06
    alcon
    0.06
    _follow
    0.06
    Activations Density 0.004%

    No Known Activations