© 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. 30497
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the script is defining or configuring an effect—i.e. on the Effect.Create/SetType/SetCategory/SetProperty calls and related EFFECT_- constants.

    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
    Smooth
    -0.07
     Autumn
    -0.07
    Gate
    -0.07
    ेल
    -0.06
    Demo
    -0.06
     jitter
    -0.06
     Shirt
    -0.06
     Expenses
    -0.06
    SHOP
    -0.06
    _lahir
    -0.06
    POSITIVE LOGITS
     trval
    0.07
    ,nil
    0.07
     prot
    0.07
     Registr
    0.06
    ไซ
    0.06
     accessToken
    0.06
    _seat
    0.06
    !↵↵↵↵↵↵
    0.06
     unnecessarily
    0.06
     resembl
    0.06
    Activations Density 0.001%

    No Known Activations