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. 30947
    Prev
    Next
    INDEX
    Explanations

    a

    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
    >(),↵
    -0.06
    .dynamic
    -0.06
     medial
    -0.06
    .jsdelivr
    -0.06
    		↵		↵		↵
    -0.06
     автом
    -0.06
    _bottom
    -0.06
     criminals
    -0.06
     Ric
    -0.06
     corridor
    -0.06
    POSITIVE LOGITS
    ,LOCATION
    0.07
    reak
    0.06
     administrators
    0.06
     McGill
    0.06
    ско
    0.06
     нанес
    0.06
    ILLS
    0.06
    an
    0.06
     sala
    0.06
    vary
    0.06
    Activations Density 0.077%

    No Known Activations