© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125278
    Prev
    Next
    INDEX
    Explanations

    states

    np_max-act · gemini-2.0-flash

    The neuron reliably flags technical mentions of thermodynamic or electronic state–density quantities (e.g. “entropy,” “density of states,” “N(E),” “DOS,” 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
    .UndefOr
    -0.07
    ouden
    -0.07
     Rugby
    -0.06
    goog
    -0.06
    723
    -0.06
     année
    -0.06
     mediated
    -0.06
     tennis
    -0.06
     analyzed
    -0.06
     proteins
    -0.06
    POSITIVE LOGITS
     ')'
    0.07
    (sq
    0.07
     vfs
    0.07
     Valve
    0.06
     volcano
    0.06
    getDrawable
    0.06
     saves
    0.06
     Kub
    0.06
    ?”↵↵
    0.06
    .swt
    0.06
    Activations Density 0.003%

    No Known Activations