© 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. 6399
    Prev
    Next
    INDEX
    Explanations

    Portal

    np_max-act · gemini-2.0-flash

    The neuron activates on proper names and key terms from the video game Portal (e.g. “GLaDOS,” “Portal,” “Aperture Science,” “Valve”).

    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
    _hp
    -0.07
     organisms
    -0.07
    _EXPRESSION
    -0.06
    houses
    -0.06
    /storage
    -0.06
    daf
    -0.06
    ,body
    -0.06
     inflammatory
    -0.06
    ‌ترین
    -0.06
    ele
    -0.06
    POSITIVE LOGITS
     aquatic
    0.06
     Entire
    0.06
     polit
    0.06
     grad
    0.06
     Patri
    0.06
     Fam
    0.06
     Bengal
    0.06
     patriarch
    0.06
     Charl
    0.06
     Dia
    0.06
    Activations Density 0.003%

    No Known Activations