© 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
    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. 42802
    Prev
    Next
    INDEX
    Explanations

    pieces, parts

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of the individual parts or subassemblies of a device (e.g. “components,” “piece,” “multi-piece,” “assemblies,” etc.).

    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
    arity
    -0.07
    ToArray
    -0.06
     Challenges
    -0.06
     Imported
    -0.06
     Blood
    -0.06
    filtro
    -0.06
     --------------------------------
    -0.06
     Filters
    -0.06
     Guid
    -0.06
    олуч
    -0.06
    POSITIVE LOGITS
     Playboy
    0.07
    ิน
    0.07
     Şah
    0.07
     whisky
    0.06
     baby
    0.06
     tér
    0.06
     docker
    0.06
     Dad
    0.06
    ented
    0.06
     jogador
    0.06
    Activations Density 0.006%

    No Known Activations