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. 19-RESID-POST-AA
    6. 77853
    Prev
    Next
    INDEX
    Explanations

    Company names

    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
     відбу
    -0.07
    اگ
    -0.06
     tub
    -0.06
    ifs
    -0.06
    ΜΠ
    -0.06
     avere
    -0.06
     코
    -0.06
    经过
    -0.05
     コ
    -0.05
     آنان
    -0.05
    POSITIVE LOGITS
    (blank
    0.08
    .CreateDirectory
    0.07
    .Month
    0.07
    рол
    0.07
    umberland
    0.07
    _declaration
    0.07
    ceries
    0.07
     náp
    0.07
     واقع
    0.07
    คาส
    0.06
    Activations Density 0.038%

    No Known Activations