© 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. 74462
    Prev
    Next
    INDEX
    Explanations

    references to web searches and research efforts

    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
    ubi
    -0.06
    alth
    -0.06
    ÑĢовод
    -0.06
    /trunk
    -0.06
    vio
    -0.06
    odore
    -0.06
    ilk
    -0.06
    esis
    -0.06
    boru
    -0.06
    igr
    -0.06
    POSITIVE LOGITS
    εÏį
    0.07
     neither
    0.07
     but
    0.07
    718
    0.06
     elsewhere
    0.06
     literal
    0.06
     none
    0.06
     online
    0.06
     literally
    0.06
    SEARCH
    0.06
    Activations Density 0.005%

    No Known Activations