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. 15-RESID-POST-AA
    6. 122792
    Prev
    Next
    INDEX
    Explanations

    technical processes

    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
     Goa
    -0.07
     Kerala
    -0.06
    σο
    -0.06
    داری
    -0.06
    ercises
    -0.06
    ifix
    -0.06
    TestData
    -0.06
    ันม
    -0.06
    拳
    -0.06
    ура
    -0.06
    POSITIVE LOGITS
    <const
    0.08
    approval
    0.08
    =NULL
    0.07
    [${
    0.07
     Petite
    0.06
     @}
    0.06
     전국
    0.06
    ráv
    0.06
     Colour
    0.06
    نگی
    0.06
    Activations Density 0.032%

    No Known Activations