© 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 EvalsExportsAPI 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. 59006
    Prev
    Next
    INDEX
    Explanations

    discussions about geopolitical concerns 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
     priv
    -0.06
    chwitz
    -0.06
    privation
    -0.06
     study
    -0.06
    íĺģ
    -0.05
    (formatter
    -0.05
     plain
    -0.05
     bạc
    -0.05
    fono
    -0.05
     Phill
    -0.05
    POSITIVE LOGITS
    ?url
    0.07
    maz
    0.07
     ØŃس
    0.07
    .Accessible
    0.07
     دÙģ
    0.07
    anoi
    0.07
    nict
    0.07
    EndPoint
    0.07
    hawk
    0.06
    [".
    0.06
    Activations Density 0.023%

    No Known Activations