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

    Neuronpedia

    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. 9407
    Prev
    Next
    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to subscription status and entitlement checks (e.g. service names, subscription information, entitlement, login/authentication).

    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
     excelente
    -0.06
     Mercy
    -0.06
    rien
    -0.06
     período
    -0.06
    romium
    -0.06
     shoulder
    -0.06
     अपर
    -0.06
    .jobs
    -0.06
    .contract
    -0.06
     Ive
    -0.06
    POSITIVE LOGITS
     vật
    0.07
     risk
    0.06
    ород
    0.06
     tapes
    0.06
    iag
    0.06
     situ
    0.06
     Aster
    0.06
     ряд
    0.06
    SSIP
    0.06
    Thank
    0.06
    Activations Density 0.358%

    No Known Activations