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. 123146
    Prev
    Next
    INDEX
    Explanations

    devices and systems

    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
     altre
    -0.07
     Av
    -0.06
    Freedom
    -0.06
     triple
    -0.06
    rength
    -0.06
     pressures
    -0.06
    adesh
    -0.06
    prices
    -0.06
     haunting
    -0.06
     parents
    -0.06
    POSITIVE LOGITS
    -Un
    0.07
    _running
    0.07
     byla
    0.06
    ظٹ
    0.06
     panor
    0.06
     <<"
    0.06
     Za
    0.06
     resultado
    0.06
     většinou
    0.06
     prů
    0.06
    Activations Density 0.099%

    No Known Activations