© 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. 7-RESID-POST-AA
    6. 127834
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    mentions of a single item or quantity—phrases or numerals indicating “one,” often in enumerations (e.g., “one … and one …”).

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    The neuron detects cardinal numbers (numerals and spelled-out small number words, especially "one"/single counts).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     già
    -0.07
    quivos
    -0.07
    Americ
    -0.07
     quando
    -0.06
     temperatura
    -0.06
     naveg
    -0.06
     عرب
    -0.06
     paralysis
    -0.06
            ↵    ↵
    -0.06
    &&&&
    -0.06
    POSITIVE LOGITS
     },
    ↵
    0.08
     организм
    0.07
    ,max
    0.06
     bufferSize
    0.06
     Mits
    0.06
    itesi
    0.06
     tooth
    0.06
    бин
    0.06
    echn
    0.06
    انی
    0.06
    Activations Density 0.013%

    No Known Activations