Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10051
    Prev
    Next
    INDEX
    Explanations

    rew

    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
    Pane
    -0.09
    .second
    -0.08
    pane
    -0.07
    fov
    -0.06
    ¤
    -0.06
    ighth
    -0.06
    .za
    -0.06
    ulta
    -0.06
    Plan
    -0.06
     Panel
    -0.06
    POSITIVE LOGITS
     sanat
    0.06
     Lydia
    0.06
     incess
    0.06
    eration
    0.06
     механи
    0.06
     торгов
    0.06
    hendis
    0.06
    _^(
    0.06
     modelo
    0.06
     görev
    0.06
    Activations Density 0.002%

    No Known Activations