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. 69036
    Prev
    Next
    INDEX
    Explanations

    _CONSTANT

    np_max-act · gemini-2.0-flash

    The neuron is triggered by floating‐point numeric literals (decimal numbers with a fractional part).

    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
     metav
    -0.07
    .Redirect
    -0.06
     نوش
    -0.06
    getter
    -0.06
    methods
    -0.06
    MODEL
    -0.06
     Fits
    -0.06
    벽
    -0.06
     неп
    -0.06
     retorna
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .Integer
    0.07
    jo
    0.06
    restaurants
    0.06
    (run
    0.06
    AGO
    0.06
    Х
    0.06
    Kent
    0.06
     Auction
    0.06
    at
    0.06
    Activations Density 0.001%

    No Known Activations