© 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. 9-LLAMASCOPE-RES-131K
    11. 98430
    Prev
    Next
    INDEX
    Explanations

    terms related to mobilization or the act of mobilizing groups or resources

    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
    yb
    -0.08
    sst
    -0.07
    ixo
    -0.07
    onaut
    -0.07
    esen
    -0.07
    iyan
    -0.06
    unya
    -0.06
    istrovstvÃŃ
    -0.06
    ollen
    -0.06
    andalone
    -0.06
    POSITIVE LOGITS
    readcr
    0.07
    foot
    0.07
     trÃŃ
    0.07
    éro
    0.07
     dụng
    0.07
    ạt
    0.06
    gest
    0.06
    ì¹Ń
    0.06
    Ïİ
    0.06
    hest
    0.06
    Activations Density 0.003%

    No Known Activations