Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 93387
    Prev
    Next
    INDEX
    Explanations

    becomes

    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
    ğında
    -0.07
    COMM
    -0.06
    ady
    -0.06
    devil
    -0.06
    _utils
    -0.06
    Pag
    -0.06
    _AHB
    -0.06
    áj
    -0.06
     дав
    -0.06
    Factor
    -0.06
    POSITIVE LOGITS
     Т
    0.07
    학회
    0.07
     responsibly
    0.07
     カ
    0.06
    _LOADED
    0.06
     жиз
    0.06
    746
    0.06
    ategoria
    0.06
    stüt
    0.06
    ignment
    0.06
    Activations Density 0.363%

    No Known Activations