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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 113402
    Prev
    Next
    INDEX
    Explanations

    idence

    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
     Double
    -0.08
     mẫu
    -0.07
    double
    -0.07
    。不过
    -0.07
    株
    -0.06
    abstractmethod
    -0.06
     Daemon
    -0.06
    .Parameters
    -0.06
    .Progress
    -0.06
    /address
    -0.06
    POSITIVE LOGITS
    vlc
    0.07
    ایان
    0.06
    /re
    0.06
    ont
    0.06
    .el
    0.06
     HAPP
    0.06
     celle
    0.06
    ToOne
    0.06
     เคร
    0.06
    /i
    0.06
    Activations Density 0.147%

    No Known Activations