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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 8273
    Prev
    Next
    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash

    The neuron detects the numeric day value (the day‐of‐month) in formatted date headers (e.g. the “15” in “October 15,”).

    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
    DispatchToProps
    -0.07
     HMAC
    -0.06
     requer
    -0.06
    Cheers
    -0.06
     '=
    -0.06
    OutOfBoundsException
    -0.06
    Evidence
    -0.06
     Eine
    -0.06
     alumnos
    -0.06
    _HOST
    -0.06
    POSITIVE LOGITS
     fg
    0.07
     underlying
    0.07
     peripherals
    0.07
    iç
    0.06
    July
    0.06
     Instrument
    0.06
     peripheral
    0.06
    fg
    0.06
    _page
    0.06
     五
    0.06
    Activations Density 0.003%

    No Known Activations