© 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. 75691
    Prev
    Next
    INDEX
    Explanations

    instances where comparisons and contextual perspectives are made

    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
    erin
    -0.07
    imax
    -0.06
     partic
    -0.06
    ÙĬÙĨÙĩ
    -0.06
    RuntimeObject
    -0.06
    illaume
    -0.06
    ánchez
    -0.06
    PrototypeOf
    -0.05
     praises
    -0.05
    خصÙĪص
    -0.05
    POSITIVE LOGITS
    atica
    0.07
     Compare
    0.07
    ulp
    0.07
    idal
    0.07
    uki
    0.07
    mie
    0.06
     typical
    0.06
    typ
    0.06
    reta
    0.06
    ãĥ³ãĥĢ
    0.06
    Activations Density 0.011%

    No Known Activations