© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron is keyed to C++ mesh‐related type names, especially occurrences of “Mesh” (e.g. “MeshType,” “mesh,” 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
    (mapping
    -0.07
    ξύ
    -0.06
     перес
    -0.06
     custody
    -0.06
     approved
    -0.06
    ,、
    -0.06
    590
    -0.06
     Walters
    -0.06
    ******
    ↵
    -0.06
    알
    -0.06
    POSITIVE LOGITS
    exual
    0.07
     Lou
    0.07
     clk
    0.07
    ϊ
    0.07
     ROM
    0.06
     Autumn
    0.06
    τες
    0.06
     almacen
    0.06
    縣
    0.06
    =query
    0.06
    Activations Density 0.023%

    No Known Activations