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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 123092
    Prev
    Next
    INDEX
    Explanations

    habits

    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
     turno
    -0.07
     sprites
    -0.07
    	placeholder
    -0.07
    texto
    -0.07
    Open
    -0.07
    _intersection
    -0.07
    ()}</
    -0.06
     й
    -0.06
     Toastr
    -0.06
    frica
    -0.06
    POSITIVE LOGITS
     habit
    0.09
     habits
    0.07
     이동
    0.07
     Behavior
    0.07
    .static
    0.06
    ันธ
    0.06
     behavior
    0.06
    ham
    0.06
     Muhammad
    0.06
     Pharma
    0.06
    Activations Density 0.012%

    No Known Activations