© 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. 56564
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession or ownership

    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
    undry
    -0.07
    _Impl
    -0.07
     addCriterion
    -0.07
    ournée
    -0.07
    eced
    -0.07
    .Networking
    -0.06
    ñana
    -0.06
    arcy
    -0.06
    eper
    -0.06
    atte
    -0.06
    POSITIVE LOGITS
    undle
    0.06
    rych
    0.06
    quiv
    0.06
    гл
    0.06
    клад
    0.06
    emann
    0.06
     wil
    0.06
    paque
    0.06
    lector
    0.06
    IDGET
    0.06
    Activations Density 0.043%

    No Known Activations