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. 73050
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     District
    -0.07
     economics
    -0.07
    Sea
    -0.07
     geometry
    -0.07
     life
    -0.07
     argument
    -0.07
     biology
    -0.06
     physics
    -0.06
     E
    -0.06
     beaches
    -0.06
    POSITIVE LOGITS
    .readyState
    0.07
     мит
    0.06
    ');?>"
    0.06
     стрем
    0.06
    _CHARSET
    0.06
    μπ
    0.06
    DBObject
    0.06
    "'↵
    0.06
    渡
    0.06
     stringBy
    0.06
    Activations Density 0.048%

    No Known Activations