© 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. 91608
    Prev
    Next
    INDEX
    Explanations

    ago

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric age references—that is, when years‐old numbers appear.

    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
     orc
    -0.07
     MUT
    -0.06
    day
    -0.06
     Salon
    -0.06
     scrollTop
    -0.06
     mut
    -0.06
     implementation
    -0.06
    Addresses
    -0.05
     doch
    -0.05
    "Do
    -0.05
    POSITIVE LOGITS
    ">//
    0.08
     eman
    0.07
    .Syntax
    0.07
     specializing
    0.06
     specialization
    0.06
     міся
    0.06
     supplied
    0.06
     Slav
    0.06
    _mux
    0.06
    _ws
    0.06
    Activations Density 0.010%

    No Known Activations