© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107089
    Prev
    Next
    INDEX
    Explanations

    demographic information related to age and household statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zas
    -0.06
    bond
    -0.06
    erox
    -0.06
    rego
    -0.06
    orthy
    -0.06
    æ¿
    -0.06
     GENERIC
    -0.06
     bonds
    -0.06
    rek
    -0.06
    astery
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
    APT
    0.07
    CellStyle
    0.07
    zik
    0.07
    oleon
    0.07
     ìĭľíĸī
    0.07
    apt
    0.07
    iran
    0.07
     Fay
    0.07
    lon
    0.06
    Activations Density 0.001%

    No Known Activations