© 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. 15-RESID-POST-AA
    6. 68749
    Prev
    Next
    INDEX
    Explanations

    dating sites and random text

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _nested
    -0.07
     ειδ
    -0.06
    _NONNULL
    -0.06
     集
    -0.06
     navigating
    -0.06
    classnames
    -0.06
     механи
    -0.06
     kennenlernen
    -0.06
    stringValue
    -0.05
     *)[
    -0.05
    POSITIVE LOGITS
    eyJ
    0.07
    만원
    0.07
     Cf
    0.06
    _Global
    0.06
    ií
    0.06
    [rand
    0.06
    Rx
    0.06
    {}'.
    0.06
     motives
    0.06
    룹
    0.06
    Activations Density 0.223%

    No Known Activations