© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13853
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on infrequent or “rare” tokens (e.g. technical jargon or uncommon words), effectively acting like an inverse‐frequency (IDF) detector.

    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
    堆
    -0.07
    textfield
    -0.07
     compliment
    -0.07
    館
    -0.06
     předpis
    -0.06
     POLIT
    -0.06
    าระ
    -0.06
    Sweden
    -0.06
     ๆ
    -0.06
     초
    -0.06
    POSITIVE LOGITS
    (blank
    0.07
     Verify
    0.06
    Nested
    0.06
     Harr
    0.06
    artin
    0.06
     rewards
    0.06
    setFont
    0.06
     iç
    0.06
     harmon
    0.06
     regain
    0.06
    Activations Density 0.087%

    No Known Activations