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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89403
    Prev
    Next
    INDEX
    Explanations

    enabling actions

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases expressing positive impact or improvement (e.g. "make a difference," "better serve," "improve," "give," "will").

    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
    事
    -0.07
    ء
    -0.06
    Mission
    -0.06
    des
    -0.06
     Christ
    -0.06
    XYZ
    -0.06
    Responsive
    -0.06
    년도
    -0.06
     persecuted
    -0.06
    Code
    -0.06
    POSITIVE LOGITS
    _rl
    0.07
    él
    0.07
     �
    0.06
     kvin
    0.06
    _chan
    0.06
     ث
    0.06
     hrom
    0.06
     дів
    0.06
     herb
    0.06
     ilma
    0.06
    Activations Density 0.068%

    No Known Activations