© 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. 121045
    Prev
    Next
    INDEX
    Explanations

    concepts related to sustainability and responsible practices across various domains

    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
    paralle
    -0.08
    ATRIX
    -0.07
    exus
    -0.07
    Çİ
    -0.07
    enstein
    -0.07
    fieldname
    -0.07
     tol
    -0.07
    ermo
    -0.07
    Touches
    -0.07
    lsru
    -0.07
    POSITIVE LOGITS
     practices
    0.09
    TM
    0.06
     escorte
    0.06
     habits
    0.06
     Fold
    0.06
    elson
    0.06
     manner
    0.06
     Practices
    0.06
     practice
    0.06
    жа
    0.06
    Activations Density 0.046%

    No Known Activations