© 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. 11-RESID-POST-AA
    6. 34098
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    narrative elements related to characters and their tasks or occupations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transparent
    -0.06
    _ABC
    -0.06
     외부
    -0.06
    ابط
    -0.06
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.06
    ../../../
    -0.06
    かに
    -0.06
    getCurrent
    -0.06
    vä
    -0.06
     aş
    -0.06
    POSITIVE LOGITS
    pollo
    0.07
    Dlg
    0.07
    ONGLONG
    0.07
    शन
    0.06
     psychosis
    0.06
     taille
    0.06
     colomb
    0.06
     Від
    0.06
    _death
    0.06
    define
    0.06
    Activations Density 0.010%

    No Known Activations