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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27176
    Prev
    Next
    INDEX
    Explanations

    elements of governmental control and regulation

    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
    lou
    -0.07
    æ©Ł
    -0.06
    جاد
    -0.06
    rlen
    -0.06
    abei
    -0.06
    æľº
    -0.06
    lesc
    -0.06
    ERSIST
    -0.06
    Mapped
    -0.06
    uš
    -0.06
    POSITIVE LOGITS
    ossier
    0.07
    olson
    0.07
     Harr
    0.06
    Choice
    0.06
     closely
    0.06
     wards
    0.06
     choice
    0.06
     Cah
    0.06
     indirectly
    0.06
     control
    0.06
    Activations Density 0.034%

    No Known Activations