© 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. 59037
    Prev
    Next
    INDEX
    Explanations

    suture

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “sut,” “suture,” “suturing,” etc., i.e. words describing surgical sutures and suturing techniques.

    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
    hton
    -0.06
     artwork
    -0.06
     enfer
    -0.06
    585
    -0.06
    EntryPoint
    -0.06
    IENT
    -0.06
     Winn
    -0.06
    ’den
    -0.06
     referencia
    -0.06
     Permit
    -0.06
    POSITIVE LOGITS
    _STORAGE
    0.07
     पहच
    0.06
     JMP
    0.06
     stu
    0.06
    랫
    0.06
     στην
    0.06
     đôi
    0.06
     BJP
    0.06
     第二
    0.06
     ''
    0.06
    Activations Density 0.008%

    No Known Activations