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. 27-RESID-POST-AA
    6. 10088
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forbidden
    -0.07
    _io
    -0.07
     Hudson
    -0.07
     Tire
    -0.07
     enclave
    -0.06
    _radius
    -0.06
     acoustic
    -0.06
     compete
    -0.06
    rieving
    -0.06
    w
    -0.06
    POSITIVE LOGITS
    fulness
    0.06
     Nov
    0.06
    .ToList
    0.06
     جلو
    0.06
    ENTICATION
    0.06
    ственного
    0.06
    >Title
    0.06
    ulmuş
    0.06
    (blog
    0.06
    .MaxLength
    0.06
    Activations Density 0.066%

    No Known Activations