© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 87901
    Prev
    Next
    INDEX
    Explanations

    terms related to lawn care and soil aeration

    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
    ansi
    -0.06
    tring
    -0.06
    stream
    -0.06
    .ix
    -0.06
     eyel
    -0.06
    etto
    -0.06
    бе
    -0.06
     Santos
    -0.06
     anarch
    -0.06
    飾
    -0.06
    POSITIVE LOGITS
    stras
    0.07
    favicon
    0.07
    udit
    0.06
    WO
    0.06
     Seeder
    0.06
    OffsetTable
    0.06
    lun
    0.06
    StackNavigator
    0.06
    _priv
    0.06
     Done
    0.06
    Activations Density 0.002%

    No Known Activations