© 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. 29969
    Prev
    Next
    INDEX
    Explanations

    lag

    np_max-act · gemini-2.0-flash

    This neuron detects references to shifting or lagging data (e.g., mentions of “shift,” “lag,” and related vector‐shifting operations).

    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
    出品
    -0.07
     endpoint
    -0.06
     Adler
    -0.06
     remorse
    -0.06
    yre
    -0.06
    ivors
    -0.06
    PLEASE
    -0.06
    Blood
    -0.06
    Salt
    -0.06
    /ms
    -0.06
    POSITIVE LOGITS
     GameState
    0.06
     Compared
    0.06
     etraf
    0.06
    ash
    0.06
     Làm
    0.06
     Luis
    0.06
     Symfony
    0.06
    _MAC
    0.06
    .defaultProps
    0.06
     UIGraphics
    0.06
    Activations Density 0.011%

    No Known Activations