© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 125204
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    does
    -0.06
    :The
    -0.06
    омі
    -0.06
     خواهند
    -0.06
    -vous
    -0.06
     Sez
    -0.06
    ’nda
    -0.06
    Chi
    -0.06
     zonder
    -0.06
     đoán
    -0.06
    POSITIVE LOGITS
     response
    0.07
     guideline
    0.07
    selling
    0.07
     '((
    0.06
    _cache
    0.06
     Disneyland
    0.06
    .tile
    0.06
     autism
    0.06
    webkit
    0.06
     Remed
    0.06
    Activations Density 0.041%

    No Known Activations