© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 78974
    Prev
    Next
    INDEX
    Explanations

    references to political and social identities, as well as movements related to nationality and culture

    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
    acha
    -0.07
    utschein
    -0.07
    inia
    -0.07
    imet
    -0.07
    ahead
    -0.07
    angi
    -0.07
    uste
    -0.07
    iÅŁim
    -0.07
    anche
    -0.07
    amburg
    -0.07
    POSITIVE LOGITS
     comfort
    0.06
     view
    0.06
    _view
    0.06
    view
    0.06
    .navigateTo
    0.06
     triang
    0.05
     mostly
    0.05
    ASTE
    0.05
    gens
    0.05
     catast
    0.05
    Activations Density 0.073%

    No Known Activations