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. 7-RESID-POST-AA
    6. 80696
    Prev
    Next
    INDEX
    Explanations

    Shiva

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     обл
    -0.07
    Measurement
    -0.07
    hhh
    -0.07
    líd
    -0.06
    Made
    -0.06
     �
    -0.06
     valores
    -0.06
     proyectos
    -0.06
    eries
    -0.06
     booked
    -0.06
    POSITIVE LOGITS
    iva
    0.10
     Invalid
    0.09
     Shiv
    0.09
    _offer
    0.09
    IVA
    0.08
    ива
    0.08
     ENGINE
    0.07
    ivr
    0.07
     Joker
    0.07
    !(
    0.07
    Activations Density 0.001%

    No Known Activations