© 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 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. 61135
    Prev
    Next
    INDEX
    Explanations

    indicators of user engagement in the form of comments and responses

    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
    hea
    -0.07
    ional
    -0.06
     getWindow
    -0.06
    440
    -0.06
    584
    -0.06
    acia
    -0.06
    allery
    -0.06
     пÑĢоÑħод
    -0.06
     Stability
    -0.06
    оÑİз
    -0.06
    POSITIVE LOGITS
     Zug
    0.07
    ruž
    0.07
    vore
    0.07
    XC
    0.06
     nét
    0.06
    kker
    0.06
    chers
    0.06
    aspers
    0.06
    ãģķãģĦ
    0.06
    oshi
    0.06
    Activations Density 0.001%

    No Known Activations