© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55801
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting words that mark key life or career milestones (e.g. retirement, arrival, discharge).

    oai_token-act-pair · o4-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
     gb
    -0.07
     paci
    -0.06
     Babe
    -0.06
    .Speed
    -0.06
     Bates
    -0.06
     Byrne
    -0.06
     cole
    -0.06
    lico
    -0.06
    _span
    -0.06
    _FEED
    -0.06
    POSITIVE LOGITS
    .UnitTesting
    0.07
    ницу
    0.07
    ном
    0.07
    )";
↵
    0.07
    .makeText
    0.06
    _MethodInfo
    0.06
     sequelize
    0.06
    中华
    0.06
    ्स
    0.06
    "io
    0.06
    Activations Density 0.035%

    No Known Activations