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. 23-RESID-POST-AA
    6. 103932
    Prev
    Next
    INDEX
    Explanations

    Medical case reports

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UBE
    -0.07
    inu
    -0.06
    ube
    -0.06
     spherical
    -0.06
    (min
    -0.06
     anesthesia
    -0.06
     inexpensive
    -0.06
     پیشنهاد
    -0.06
    身
    -0.06
     competitiveness
    -0.06
    POSITIVE LOGITS
    _REG
    0.07
     provoked
    0.07
    .jasper
    0.07
     ctxt
    0.06
    ":"","
    0.06
    Fax
    0.06
    цию
    0.06
    ?family
    0.06
    .stdout
    0.06
    .expand
    0.06
    Activations Density 0.201%

    No Known Activations