© 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. 31935
    Prev
    Next
    INDEX
    Explanations

    suicidal

    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
     Gulf
    -0.07
    压
    -0.07
    _tD
    -0.07
     Storage
    -0.06
    Bah
    -0.06
     Rac
    -0.06
     disposit
    -0.06
     Heads
    -0.06
    ("**
    -0.06
    енка
    -0.06
    POSITIVE LOGITS
     sass
    0.07
    无
    0.07
     піс
    0.07
     ;;↵
    0.06
    '||
    0.06
    -ม
    0.06
    無
    0.06
    !");↵
    0.06
    veled
    0.06
     ориг
    0.06
    Activations Density 0.119%

    No Known Activations