© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94664
    Prev
    Next
    INDEX
    Explanations

    terms related to the deformation and shaping of objects in a mathematical context

    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
    ahn
    -0.06
     Operation
    -0.06
    ayo
    -0.06
     MAR
    -0.06
     marshal
    -0.06
    atters
    -0.06
     TU
    -0.06
     AV
    -0.06
    ηÏĥη
    -0.06
    ethe
    -0.05
    POSITIVE LOGITS
    å±
    0.08
    ¦
    0.07
    ůr
    0.07
    ollah
    0.07
     PROCUREMENT
    0.07
    StackNavigator
    0.07
    FFFFFFFF
    0.07
    æݧ
    0.07
     dụ
    0.07
    heel
    0.07
    Activations Density 0.003%

    No Known Activations