© 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. 7921
    Prev
    Next
    INDEX
    Explanations

    possessives

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases that denote breaking something down into constituent or minimal units (e.g., “units,” “constituent parts,” “breaking down,” “individual”).

    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
    UPPORT
    -0.07
    por
    -0.07
    (utils
    -0.07
     empathy
    -0.06
     industrial
    -0.06
    IFO
    -0.06
     PUR
    -0.06
     universal
    -0.06
     enough
    -0.06
    oxic
    -0.06
    POSITIVE LOGITS
     Manafort
    0.08
    /apache
    0.07
    /T
    0.06
    _suspend
    0.06
     Prof
    0.06
    _based
    0.06
    {/
    0.06
    _spell
    0.06
     NSW
    0.06
     purchaser
    0.06
    Activations Density 0.009%

    No Known Activations