© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 72899
    Prev
    Next
    INDEX
    Explanations

    elements related to future aspirations or plans

    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
    shima
    -0.07
    erp
    -0.07
    anvas
    -0.07
    azes
    -0.07
    jedn
    -0.07
    boro
    -0.06
    éļª
    -0.06
    ervo
    -0.06
    boru
    -0.06
    engo
    -0.06
    POSITIVE LOGITS
     will
    0.09
    will
    0.08
     helps
    0.07
    ä¼ļ
    0.07
    Will
    0.07
     поможеÑĤ
    0.06
    æľĥ
    0.06
     help
    0.06
     sẽ
    0.06
     ÑģÑĤанеÑĤ
    0.06
    Activations Density 0.012%

    No Known Activations