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. 112302
    Prev
    Next
    INDEX
    Explanations

    History

    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
     realidad
    -0.07
    Чер
    -0.07
    .Get
    -0.06
     absorb
    -0.06
    	cell
    -0.06
     relev
    -0.06
     senza
    -0.06
     mask
    -0.06
     interests
    -0.06
     quelle
    -0.06
    POSITIVE LOGITS
    ppelin
    0.07
     trưng
    0.07
    550
    0.07
     yapıyor
    0.06
    .xaxis
    0.06
    ніцип
    0.06
    イス
    0.06
    _callbacks
    0.06
    itures
    0.06
     Rif
    0.06
    Activations Density 0.009%

    No Known Activations