© 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. 703
    Prev
    Next
    INDEX
    Explanations

    Unit, system

    np_max-act · gemini-2.0-flash

    The neuron detects HVAC‐related technical terms and model/specification names (e.g. “HVAC,” “Hydron Module,” “SEER,” “airflow,” specific equipment models).

    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
     bunlar
    -0.07
    etections
    -0.07
    _messages
    -0.06
     сайті
    -0.06
    socket
    -0.06
    ично
    -0.06
    astered
    -0.06
    static
    -0.06
    Accept
    -0.06
     slammed
    -0.06
    POSITIVE LOGITS
     dur
    0.06
     مط
    0.06
     SAM
    0.06
    _',
    0.06
     клад
    0.06
     трансп
    0.06
    ALLEL
    0.06
     Fuse
    0.06
     Automobile
    0.06
    ۰
    0.06
    Activations Density 0.036%

    No Known Activations