© 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
    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. 8847
    Prev
    Next
    INDEX
    Explanations

    omp

    np_max-act · gemini-2.0-flash

    The neuron is a specialist detector for standout technical or scientific proper nouns and acronyms—e.g. gene names (ompA), organism or disease names (Influenza A, B. wadsworthia), branded equipment names, and other capitalized terms.

    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
     Logical
    -0.07
    INVALID
    -0.07
    Patterns
    -0.06
     Sorted
    -0.06
    micro
    -0.06
    skins
    -0.06
    Pragma
    -0.06
     bottles
    -0.06
    /Core
    -0.06
    ibase
    -0.06
    POSITIVE LOGITS
    劉
    0.07
     ikt
    0.07
     sistemi
    0.06
    Checker
    0.06
    _pow
    0.06
     उन
    0.06
    >",
    0.06
    ้า
    0.06
    >((
    0.06
     лі
    0.06
    Activations Density 0.110%

    No Known Activations