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. 19-RESID-POST-AA
    6. 9676
    Prev
    Next
    INDEX
    Explanations

    Medical questions

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prey
    -0.06
    атку
    -0.06
    Sequential
    -0.06
    اذا
    -0.06
    HttpRequest
    -0.06
    ію
    -0.06
    ศาสตร
    -0.06
    _EDITOR
    -0.06
    яться
    -0.06
    ttp
    -0.06
    POSITIVE LOGITS
     отв
    0.07
    ρός
    0.06
    inson
    0.06
    spell
    0.06
     Performance
    0.06
     Gesture
    0.06
    -sizing
    0.06
     Aval
    0.06
     authService
    0.06
     виконання
    0.06
    Activations Density 0.047%

    No Known Activations