© 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. 17-LLAMASCOPE-RES-131K
    11. 117852
    Prev
    Next
    INDEX
    Explanations

    references to data structures and data management concepts

    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
    Type
    -0.08
    ships
    -0.07
    bo
    -0.07
    _datasets
    -0.07
    ãĥ«ãĥī
    -0.07
    inz
    -0.07
    box
    -0.07
    mente
    -0.07
    DataSource
    -0.07
    ance
    -0.07
    POSITIVE LOGITS
    ë²ł
    0.10
    ils
    0.10
    :image
    0.09
    centers
    0.09
    -aos
    0.08
    flow
    0.08
    /Instruction
    0.08
    center
    0.08
    fono
    0.07
    cube
    0.07
    Activations Density 0.073%

    No Known Activations