© 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. 129898
    Prev
    Next
    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of quantitative path‐finding metrics—terms like “shortest,” “distance,” and “paths” when describing algorithmic distances.

    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
     Ed
    -0.07
    ่วย
    -0.06
     Spiral
    -0.06
    _goto
    -0.06
     Defendants
    -0.06
    isoner
    -0.06
    Borders
    -0.06
     Sherman
    -0.06
    ونی
    -0.06
     Tome
    -0.06
    POSITIVE LOGITS
    lopen
    0.07
    -phase
    0.07
     kita
    0.06
     HomeComponent
    0.06
     sperm
    0.06
     saya
    0.06
     κο
    0.06
     dollar
    0.06
     forth
    0.06
     pepp
    0.06
    Activations Density 0.013%

    No Known Activations