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. 45220
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ?↵↵↵
    -0.06
    Tip
    -0.06
     tengo
    -0.06
     tenemos
    -0.06
     любов
    -0.06
     preach
    -0.05
    ?:
    -0.05
     newValue
    -0.05
     Laugh
    -0.05
    ycop
    -0.05
    POSITIVE LOGITS
    _upgrade
    0.07
     Alzheimer
    0.07
    =\"#
    0.07
     centroid
    0.07
     boundary
    0.07
    (canvas
    0.06
     Notifications
    0.06
     jams
    0.06
    administr
    0.06
     component
    0.06
    Activations Density 0.036%

    No Known Activations