© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6257
    Prev
    Next
    INDEX
    Explanations

    prospective

    np_max-act · gemini-2.0-flash

    The neuron activates on clinical‐research study–design terms—especially “prospective” (and related words like “randomized,” “observational,” “cohort,” or “evaluation”).

    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
     Rain
    -0.06
    _Config
    -0.06
     bread
    -0.06
    ум
    -0.06
     Bat
    -0.06
    aclass
    -0.06
    عنی
    -0.06
    iomanip
    -0.06
    hel
    -0.06
    .Entry
    -0.06
    POSITIVE LOGITS
     prospective
    0.08
     speculation
    0.07
     axiom
    0.07
     исключ
    0.07
     무엇
    0.07
    value
    0.07
    Animated
    0.07
     paranormal
    0.07
     posX
    0.07
    ?><?
    0.07
    Activations Density 0.003%

    No Known Activations