© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 30760
    Prev
    Next
    INDEX
    Explanations

    ethyl

    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
    angelog
    -0.08
     ایجاد
    -0.07
    라고
    -0.06
    icates
    -0.06
    toBeInTheDocument
    -0.06
     یک
    -0.06
    ‌کند
    -0.06
    ině
    -0.06
     του
    -0.06
    ayas
    -0.06
    POSITIVE LOGITS
    dateTime
    0.07
     MISSING
    0.07
    civil
    0.06
     getHeight
    0.06
    luv
    0.06
    commission
    0.06
    。不过
    0.06
     deadline
    0.06
    fred
    0.06
    _INSTALL
    0.06
    Activations Density 0.004%

    No Known Activations