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. 50969
    Prev
    Next
    INDEX
    Explanations

    file paths/code

    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
    вед
    -0.07
    -edge
    -0.07
    _statement
    -0.07
    (~
    -0.07
    (spec
    -0.06
    abstractmethod
    -0.06
    Still
    -0.06
     condos
    -0.06
    fortunately
    -0.06
     ""},↵
    -0.06
    POSITIVE LOGITS
     місці
    0.07
    'ın
    0.06
     SMA
    0.06
    expires
    0.06
     brib
    0.06
     lineback
    0.06
     hesitate
    0.06
    jumlah
    0.06
     uvol
    0.06
    .Menu
    0.06
    Activations Density 0.088%

    No Known Activations