© 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. 19-RESID-POST-AA
    6. 71030
    Prev
    Next
    INDEX
    Explanations

    Size

    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
     CONDITIONS
    -0.06
    450
    -0.06
    Danger
    -0.06
     Jahre
    -0.06
    stal
    -0.06
    455
    -0.06
     lump
    -0.06
     Chrome
    -0.06
    .Navigator
    -0.06
     KeyEvent
    -0.06
    POSITIVE LOGITS
     MUSIC
    0.07
    ضی
    0.06
     assists
    0.06
    _BUFFER
    0.06
    TextLabel
    0.06
     suppose
    0.06
     MI
    0.06
    oday
    0.06
     Gamb
    0.06
     oppression
    0.06
    Activations Density 0.034%

    No Known Activations