© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70921
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and ages

    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
    á»įc
    -0.08
    Ãłn
    -0.07
    _icall
    -0.07
    åĬĽçļĦ
    -0.07
    ergus
    -0.07
    лÑĥг
    -0.07
    untas
    -0.07
    weep
    -0.07
    rawer
    -0.07
    MUX
    -0.07
    POSITIVE LOGITS
     adel
    0.06
    idar
    0.06
    adar
    0.06
    idos
    0.06
    vert
    0.06
     Meter
    0.05
    _dispatcher
    0.05
    atch
    0.05
     ilma
    0.05
     kuv
    0.05
    Activations Density 0.003%

    No Known Activations