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. 19-RESID-POST-AA
    6. 83377
    Prev
    Next
    INDEX
    Explanations

    to

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vander
    -0.07
    ]));↵↵
    -0.06
     /\.
    -0.06
    .entrySet
    -0.06
    ')}</
    -0.06
     Мас
    -0.06
    Ma
    -0.06
    ustomer
    -0.06
    Pop
    -0.06
    Makes
    -0.06
    POSITIVE LOGITS
    _OF
    0.07
     üniversit
    0.07
     drafted
    0.07
    _lcd
    0.07
    GES
    0.06
     enforcement
    0.06
     araştır
    0.06
    úsqueda
    0.06
     RA
    0.06
     blinking
    0.06
    Activations Density 0.000%

    No Known Activations