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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40271
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to mathematical concepts, specifically involving graphs and properties within graph theory

    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
    ãĥĢãĤ¤
    -0.06
    arest
    -0.06
     Parcel
    -0.06
    ิร
    -0.05
     quint
    -0.05
     Stanton
    -0.05
     McMaster
    -0.05
     tort
    -0.05
    ibri
    -0.05
     bay
    -0.05
    POSITIVE LOGITS
    smarty
    0.07
    erç
    0.07
    uras
    0.07
    ä¿®
    0.07
    Ñģем
    0.07
    ëľ
    0.07
    covered
    0.07
    çĽijåIJ¬é¡µéĿ¢
    0.07
    rlen
    0.07
     Sands
    0.07
    Activations Density 0.048%

    No Known Activations