© 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. 4575
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning and strategy formulation

    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
    olare
    -0.09
    eyer
    -0.08
    asu
    -0.07
    elter
    -0.07
    bour
    -0.07
    uras
    -0.07
    andelier
    -0.07
    elp
    -0.07
    iani
    -0.07
    лÑĥÑĩ
    -0.07
    POSITIVE LOGITS
     Pap
    0.07
    :NSLocalizedString
    0.06
     alternate
    0.05
     counter
    0.05
    .gov
    0.05
     Sat
    0.05
    Sock
    0.05
     berk
    0.05
     neutral
    0.05
     instead
    0.05
    Activations Density 0.011%

    No Known Activations