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. 9975
    Prev
    Next
    INDEX
    Explanations

    Questioning

    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
     SPACE
    -0.07
    dělen
    -0.07
    Blank
    -0.07
     abych
    -0.07
     وت
    -0.06
     dangerously
    -0.06
     locus
    -0.06
    -index
    -0.06
    -"+
    -0.06
    />
    -0.06
    POSITIVE LOGITS
     Newtonsoft
    0.07
    ernen
    0.06
    .userAgent
    0.06
    _Renderer
    0.06
     Основ
    0.06
    шка
    0.06
     Mayweather
    0.06
    aris
    0.06
    रल
    0.06
    /response
    0.06
    Activations Density 0.016%

    No Known Activations