© 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 EvalsExportsinterp-engineNEWAPI 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. 95282
    Prev
    Next
    INDEX
    Explanations

    concepts related to support and community care within an educational setting

    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
    rex
    -0.07
    eno
    -0.06
    laz
    -0.06
    istr
    -0.06
    anz
    -0.06
    lasses
    -0.06
    uggage
    -0.06
    ovich
    -0.06
    ilon
    -0.06
    stract
    -0.06
    POSITIVE LOGITS
     Gros
    0.07
    forman
    0.07
    IEW
    0.07
    SSIP
    0.07
     IRequest
    0.06
    éľ
    0.06
    conto
    0.06
     orient
    0.06
    chwitz
    0.06
     Scho
    0.06
    Activations Density 0.004%

    No Known Activations