© 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. 68736
    Prev
    Next
    INDEX
    Explanations

    NotFoundError

    np_max-act · gemini-2.0-flash

    The neuron activates on Python “ModuleNotFoundError: No module named …” messages indicating missing modules.

    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
     業
    -0.07
    olecular
    -0.07
    (em
    -0.07
     unions
    -0.07
     Takes
    -0.06
     Identity
    -0.06
     motivations
    -0.06
     derived
    -0.06
     union
    -0.06
    Identity
    -0.06
    POSITIVE LOGITS
    cla
    0.08
    ClassNotFoundException
    0.07
     전에
    0.07
    hong
    0.06
    一种
    0.06
     pne
    0.06
    函
    0.06
    σσα
    0.06
    NotFoundException
    0.06
    writeln
    0.06
    Activations Density 0.002%

    No Known Activations