© 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. 15014
    Prev
    Next
    INDEX
    Explanations

    terms related to planning and goal-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
    decltype
    -0.08
    quier
    -0.08
    elden
    -0.07
    rita
    -0.07
    Formatter
    -0.07
    Chance
    -0.06
    edl
    -0.06
    elters
    -0.06
    edir
    -0.06
    uyu
    -0.06
    POSITIVE LOGITS
     for
    0.07
     based
    0.07
     suitable
    0.06
    erus
    0.06
    ìĤ¬ë¥¼
    0.06
    based
    0.06
     длÑı
    0.06
     untuk
    0.06
    sig
    0.06
    iche
    0.06
    Activations Density 0.035%

    No Known Activations