Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12867
    Prev
    Next
    INDEX
    Explanations

    around/round

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are parts of decimal numbers (i.e. numeric tokens containing a dot and digits).

    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
     COLOR
    -0.06
     below
    -0.06
     recieved
    -0.06
     threshold
    -0.06
    telegram
    -0.06
    -buffer
    -0.06
     openFileDialog
    -0.06
     connectors
    -0.06
     dét
    -0.06
     %(
    -0.06
    POSITIVE LOGITS
    лу
    0.08
     bán
    0.07
    旁
    0.07
    ROC
    0.06
     üretim
    0.06
     olmak
    0.06
     simulated
    0.06
    UIView
    0.06
     impass
    0.06
    Inicio
    0.06
    Activations Density 0.015%

    No Known Activations