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. 123472
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific texts

    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
    Increases
    -0.08
     applicant
    -0.07
     weighs
    -0.07
    /configuration
    -0.07
    configured
    -0.06
    ",-
    -0.06
    panse
    -0.06
    Solution
    -0.06
     papers
    -0.06
     comparative
    -0.06
    POSITIVE LOGITS
     слишком
    0.06
     optimistic
    0.06
    ผม
    0.06
    ー
    0.06
    UIBarButtonItem
    0.06
    ◎
    0.06
     Neck
    0.06
    :".
    0.06
    _tensors
    0.06
     vero
    0.05
    Activations Density 0.162%

    No Known Activations