© 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. 40475
    Prev
    Next
    INDEX
    Explanations

    phrases relating to location and positioning within a 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
     crossorigin
    -0.08
    /Branch
    -0.07
    immer
    -0.07
     elsewhere
    -0.07
    .scalablytyped
    -0.07
     дÑĢÑĥгого
    -0.07
     another
    -0.06
    another
    -0.06
    веÑī
    -0.06
    /welcome
    -0.06
    POSITIVE LOGITS
     mostly
    0.08
     which
    0.07
    alim
    0.07
    caff
    0.07
    Ä
    0.06
    NOP
    0.06
     pÅĻiÄįemž
    0.06
    mostly
    0.06
    íij¸
    0.06
    pter
    0.06
    Activations Density 0.042%

    No Known Activations