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. 30503
    Prev
    Next
    INDEX
    Explanations

    maintenance

    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
    .The
    -0.09
     The
    -0.08
     the
    -0.08
     Clintons
    -0.07
    ethe
    -0.07
     apology
    -0.07
    	the
    -0.07
    nya
    -0.07
    verts
    -0.06
    .buy
    -0.06
    POSITIVE LOGITS
     handleError
    0.06
    ‌است
    0.06
     Rab
    0.06
    (localStorage
    0.06
    _sta
    0.06
     ISSN
    0.06
     $?
    0.06
    MainActivity
    0.06
    TestingModule
    0.06
    /use
    0.06
    Activations Density 0.396%

    No Known Activations