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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89903
    Prev
    Next
    INDEX
    Explanations

    maintenance

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “maintenance” (especially in treatment or study contexts), pinpointing references to maintenance-phase therapy.

    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
     Cameras
    -0.06
     Corrections
    -0.06
     scheduling
    -0.06
     effort
    -0.05
     Sometimes
    -0.05
     report
    -0.05
    岩
    -0.05
     Abilities
    -0.05
    Ray
    -0.05
    chemes
    -0.05
    POSITIVE LOGITS
     CONT
    0.07
     SCE
    0.07
    -‐
    0.07
     maintenance
    0.07
    �
    0.06
    ,,
    0.06
    students
    0.06
     consolidated
    0.06
    <dynamic
    0.06
     Cp
    0.06
    Activations Density 0.005%

    No Known Activations