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. 27-RESID-POST-AA
    6. 10466
    Prev
    Next
    INDEX
    Explanations

    ErrorMessage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ียรต
    -0.07
    ?
    -0.07
    �
    -0.07
    _QUOTES
    -0.07
    __":↵
    -0.07
    (section
    -0.06
     pair
    -0.06
     );↵↵↵
    -0.06
    mov
    -0.06
    featured
    -0.06
    POSITIVE LOGITS
     trị
    0.06
    _col
    0.06
     northern
    0.06
     honorary
    0.06
    γο
    0.06
    .di
    0.05
     ケ
    0.05
     defamation
    0.05
     predators
    0.05
     glVertex
    0.05
    Activations Density 0.320%

    No Known Activations