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. 11-RESID-POST-AA
    6. 123699
    Prev
    Next
    INDEX
    Explanations

    for

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     storing
    -0.10
     complex
    -0.08
     compound
    -0.07
     measuring
    -0.07
     insertion
    -0.06
     complexes
    -0.06
    icao
    -0.06
     Estimates
    -0.06
     Find
    -0.06
    _dept
    -0.06
    POSITIVE LOGITS
     opted
    0.09
     opting
    0.07
     opt
    0.07
    ılım
    0.07
    -Russian
    0.07
    opts
    0.07
    раж
    0.07
    ortic
    0.06
     halves
    0.06
     "/",
    0.06
    Activations Density 0.019%

    No Known Activations