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. 19-RESID-POST-AA
    6. 91610
    Prev
    Next
    INDEX
    Explanations

    legal requirements

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tarihi
    -0.07
    }],↵
    -0.06
    }`);↵↵
    -0.06
    gin
    -0.06
    lady
    -0.06
     Dolphins
    -0.06
    ')↵↵
    -0.06
     [
    -0.06
    "↵↵
    -0.06
    <"
    -0.06
    POSITIVE LOGITS
    .Local
    0.07
     actu
    0.07
     refere
    0.07
    :self
    0.06
     driveway
    0.06
    .getSession
    0.06
     unsus
    0.06
     Mặt
    0.06
    واء
    0.06
    puted
    0.06
    Activations Density 0.026%

    No Known Activations