© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 18394
    Prev
    Next
    INDEX
    Explanations

    ×

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oin
    -0.06
    ा�
    -0.06
     ένας
    -0.06
     �
    -0.06
     Luft
    -0.06
    /stats
    -0.06
    orig
    -0.06
     :-)
    -0.06
    ็นส
    -0.06
    戴
    -0.06
    POSITIVE LOGITS
     moto
    0.08
    piring
    0.07
     inputs
    0.07
    .HttpServlet
    0.06
    phanumeric
    0.06
     nécess
    0.06
    ştir
    0.06
    ци
    0.06
     animations
    0.06
    Tel
    0.06
    Activations Density 0.001%

    No Known Activations