Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8627
    Prev
    Next
    INDEX
    Explanations

    intelligence

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of superhuman or psychic abilities (e.g. telekinesis, telepathy, mind control).

    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
    efd
    -0.07
     video
    -0.07
    dete
    -0.06
    574
    -0.06
     color
    -0.06
     setUp
    -0.06
    iu
    -0.06
     thugs
    -0.06
    azzo
    -0.06
    war
    -0.06
    POSITIVE LOGITS
    返回
    0.07
    Boost
    0.06
     Playlist
    0.06
     Mes
    0.06
    %',
    0.06
    -CN
    0.06
    .strip
    0.06
     tem
    0.06
     Creat
    0.06
    提升
    0.06
    Activations Density 0.110%

    No Known Activations