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. 11-RESID-POST-AA
    6. 35954
    Prev
    Next
    INDEX
    Explanations

    one

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .sleep
    -0.07
    etsy
    -0.06
    _SETTINGS
    -0.06
    _male
    -0.06
     CCD
    -0.06
     Violence
    -0.06
     reflective
    -0.06
    ician
    -0.06
     cpu
    -0.06
    ابان
    -0.06
    POSITIVE LOGITS
     verr
    0.07
    VertexArray
    0.07
    (_("
    0.06
     идет
    0.06
    のが
    0.06
     ガ
    0.06
     ความ
    0.06
     loaf
    0.06
     subtly
    0.06
    /ge
    0.06
    Activations Density 0.027%

    No Known Activations