© 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. 70043
    Prev
    Next
    INDEX
    Explanations

    themes related to social structures and leadership

    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
    ith
    -0.08
    LETE
    -0.07
     sais
    -0.07
    Contains
    -0.07
    907
    -0.07
    904
    -0.07
    ÅŁt
    -0.07
    _IOC
    -0.06
    eps
    -0.06
    .ends
    -0.06
    POSITIVE LOGITS
     means
    0.10
    æĦıåij³
    0.08
    means
    0.08
     requires
    0.07
     is
    0.07
     isn
    0.07
     Means
    0.07
     significa
    0.07
     would
    0.07
     doesn
    0.06
    Activations Density 0.265%

    No Known Activations