© 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. 104578
    Prev
    Next
    INDEX
    Explanations

    elements related to governance and military strategy

    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
    kap
    -0.08
    adro
    -0.08
    avig
    -0.07
    éĢĴ
    -0.07
    .bb
    -0.07
    ẽ
    -0.07
     procur
    -0.07
     currently
    -0.06
     bev
    -0.06
     detriment
    -0.06
    POSITIVE LOGITS
    ational
    0.07
     soon
    0.07
    ÄĽl
    0.07
    soon
    0.07
     Soon
    0.06
    suffix
    0.06
     slogan
    0.06
    ident
    0.06
     GetMessage
    0.06
     MessageType
    0.06
    Activations Density 0.001%

    No Known Activations