© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57078
    Prev
    Next
    INDEX
    Explanations

    Wanting, needing, wishing

    np_max-act · gemini-2.0-flash

    This neuron detects first‐person “I want” or “I need” phrases expressing the asker’s desired outcome.

    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
    Generally
    -0.07
     indicators
    -0.07
    putation
    -0.06
     putchar
    -0.06
    Roger
    -0.06
     getContentPane
    -0.06
    spy
    -0.06
     review
    -0.06
     ding
    -0.06
    リ
    -0.06
    POSITIVE LOGITS
     Grund
    0.07
    TOT
    0.07
    (__
    0.06
    .ObjectMeta
    0.06
     ResultSet
    0.06
    ають
    0.06
    VF
    0.06
    undaki
    0.06
    ंक
    0.06
    _nn
    0.06
    Activations Density 0.078%

    No Known Activations