© 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. 88185
    Prev
    Next
    INDEX
    Explanations

    numbers indicating age or significant milestones related to individuals

    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
     Cosmetic
    -0.06
     cosmetic
    -0.06
    Ãłi
    -0.06
    ÑĦи
    -0.06
    zm
    -0.06
     protocols
    -0.06
     Nev
    -0.06
     bic
    -0.06
    ì
    -0.06
    одÑĭ
    -0.05
    POSITIVE LOGITS
    ALER
    0.07
    annis
    0.07
    utters
    0.07
    usher
    0.07
    storeId
    0.06
    ksam
    0.06
    celed
    0.06
    utter
    0.06
    isable
    0.06
    448
    0.06
    Activations Density 0.004%

    No Known Activations