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. 3-RESID-POST-AA
    6. 122472
    Prev
    Next
    INDEX
    Explanations

    Way

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /tutorial
    -0.07
    _statement
    -0.07
    IBILITY
    -0.06
    Collapse
    -0.06
    return
    -0.06
     arom
    -0.06
    rolled
    -0.06
    FFT
    -0.06
     вклад
    -0.06
     레벨
    -0.06
    POSITIVE LOGITS
     Milky
    0.21
     Way
    0.11
     нев
    0.11
     whopping
    0.09
     generous
    0.07
     많은
    0.07
     Guinness
    0.07
     WAY
    0.07
    (DbContext
    0.06
     way
    0.06
    Activations Density 0.002%

    No Known Activations