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. 3-RESID-POST-AA
    6. 122274
    Prev
    Next
    INDEX
    Explanations

    ferguson

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unst
    -0.07
    884
    -0.07
     Monroe
    -0.06
     potentials
    -0.06
    acciones
    -0.06
     удив
    -0.06
     MUCH
    -0.06
    883
    -0.06
     Alumni
    -0.06
     resistor
    -0.06
    POSITIVE LOGITS
     Ferguson
    0.38
    erguson
    0.27
    ergus
    0.10
    avanaugh
    0.08
     Wenger
    0.07
    :]↵↵
    0.07
    "));
    ↵
    ↵
    0.07
     シ
    0.07
     >",
    0.07
    """↵↵
    0.07
    Activations Density 0.001%

    No Known Activations