© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57991
    Prev
    Next
    INDEX
    Explanations

    Organization names

    np_max-act · gemini-2.0-flash

    The neuron activates on multiword proper-name phrases denoting formal institutions, programs, events, or legislative acts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     him
    -0.07
    	Logger
    -0.07
    Seats
    -0.06
    _videos
    -0.06
    cases
    -0.06
    883
    -0.06
    Mer
    -0.06
     této
    -0.06
    _THREADS
    -0.06
    zim
    -0.06
    POSITIVE LOGITS
    eci
    0.08
    ):
↵
↵
    0.07
    actually
    0.07
     lỗi
    0.06
     armor
    0.06
    овые
    0.06
    $_['
    0.06
     sidewalks
    0.06
     cler
    0.06
    ually
    0.06
    Activations Density 0.072%

    No Known Activations