© 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. 29964
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron responds to special conversation/formatting markers (the model’s control tokens like “<|start_header_id|>”).

    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
    //
    -0.06
     AppConfig
    -0.06
    .§
    -0.06
    ,对
    -0.06
    Προ
    -0.06
     нек
    -0.06
    .UndefOr
    -0.06
     sele
    -0.06
    Moon
    -0.06
     указ
    -0.06
    POSITIVE LOGITS
    xED
    0.07
    øre
    0.06
    nection
    0.06
     },{
    0.06
    _lane
    0.06
    loses
    0.06
    ować
    0.06
    MPI
    0.06
     glBegin
    0.06
    sorry
    0.06
    Activations Density 0.108%

    No Known Activations