Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 11135
    Prev
    Next
    INDEX
    Explanations

    musical scores descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -information
    -0.07
    adult
    -0.07
    _FT
    -0.06
     depot
    -0.06
    Fit
    -0.06
    отов
    -0.06
    Songs
    -0.06
    Elite
    -0.06
     khỏi
    -0.06
     staveb
    -0.06
    POSITIVE LOGITS
    ové
    0.06
    ahkan
    0.06
    660
    0.06
    getView
    0.06
     густ
    0.06
     motion
    0.06
    mmas
    0.06
     Subscriber
    0.06
     *)__
    0.06
    _angle
    0.06
    Activations Density 0.018%

    No Known Activations