© 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. 123934
    Prev
    Next
    INDEX
    Explanations

    descriptions of social issues and representation in media or 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
    oba
    -0.08
    ilog
    -0.07
    rish
    -0.07
    anik
    -0.06
    efon
    -0.06
    agn
    -0.06
    _TestCase
    -0.06
    ooter
    -0.06
    à¥įन
    -0.06
    ucha
    -0.06
    POSITIVE LOGITS
     conventional
    0.11
     mainstream
    0.10
     other
    0.09
     usual
    0.08
     traditional
    0.08
    optera
    0.07
     standard
    0.07
    unless
    0.07
     wider
    0.07
     standart
    0.07
    Activations Density 0.044%

    No Known Activations