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. 73262
    Prev
    Next
    INDEX
    Explanations

    "a la" phrases

    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
    (indices
    -0.07
     library
    -0.07
    _index
    -0.07
     ogl
    -0.07
    driver
    -0.06
     himself
    -0.06
     tossed
    -0.06
    >>>>>>>
    -0.06
     imageUrl
    -0.06
    anga
    -0.06
    POSITIVE LOGITS
     TimeUnit
    0.07
     BufferedReader
    0.06
     androidx
    0.06
     evolves
    0.06
    ้ช
    0.06
    _MORE
    0.05
    梅
    0.05
    _pll
    0.05
    CLS
    0.05
     besar
    0.05
    Activations Density 0.119%

    No Known Activations