© 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. 91347
    Prev
    Next
    INDEX
    Explanations

    calculations

    np_max-act · gemini-2.0-flash

    The neuron activates on statistical‐variance and dispersion terms (e.g. “variance,” “Var,” related numeric variance calculations).

    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
    寻
    -0.08
     generator
    -0.08
     planet
    -0.07
     dogs
    -0.07
     Carousel
    -0.07
    แล
    -0.07
     Eco
    -0.07
     Zoom
    -0.06
     mess
    -0.06
     moments
    -0.06
    POSITIVE LOGITS
    　�
    0.08
     فرهنگ
    0.07
    	Query
    0.06
    ]=="
    0.06
     *)__
    0.06
     v
    0.06
    .LayoutInflater
    0.06
    ultural
    0.06
     $($
    0.06
    /tr
    0.06
    Activations Density 0.089%

    No Known Activations