© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25355
    Prev
    Next
    INDEX
    Explanations

    Coordinates

    np_max-act · gemini-2.0-flash

    The neuron is activated by numeric tokens representing floating‐point values (decimal numbers) in technical data.

    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
     beer
    -0.07
    Compare
    -0.06
    Licensed
    -0.06
    Semaphore
    -0.06
    Red
    -0.06
     Alexand
    -0.06
    -functional
    -0.06
     trainers
    -0.06
     red
    -0.06
    Army
    -0.06
    POSITIVE LOGITS
    MFLOAT
    0.07
    (klass
    0.07
     glGet
    0.07
     движения
    0.07
     Açık
    0.07
    _Init
    0.07
    _dl
    0.06
     واب
    0.06
    _MM
    0.06
    otify
    0.06
    Activations Density 0.003%

    No Known Activations