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. 7-RESID-POST-AA
    6. 10544
    Prev
    Next
    INDEX
    Explanations

    atic

    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
     storyline
    -0.07
     hudeb
    -0.07
     Toni
    -0.07
    ridor
    -0.06
    들을
    -0.06
     Medal
    -0.06
     справа
    -0.06
    -stock
    -0.06
    онь
    -0.06
     Marl
    -0.06
    POSITIVE LOGITS
    _PAGE
    0.07
    .indexOf
    0.07
    atic
    0.06
     pancreatic
    0.06
    днання
    0.06
    галтер
    0.06
    _BOUND
    0.06
    avigator
    0.06
    [g
    0.06
     statewide
    0.06
    Activations Density 0.001%

    No Known Activations