© 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. 3125
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to topology and geometry

    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
    ospace
    -0.09
    inness
    -0.08
    ichick
    -0.07
    azzo
    -0.07
    SPATH
    -0.07
    cken
    -0.07
    UNET
    -0.07
    маз
    -0.07
    ÑĩиÑħ
    -0.07
    etting
    -0.07
    POSITIVE LOGITS
     group
    0.09
    -group
    0.07
     Group
    0.07
     subgroup
    0.07
     Gast
    0.06
    group
    0.06
    igid
    0.06
    ân
    0.06
     GROUP
    0.06
     groups
    0.06
    Activations Density 0.041%

    No Known Activations