© 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. 124068
    Prev
    Next
    INDEX
    Explanations

    XML-like markup syntax and code annotations

    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
    ses
    -0.09
    nt
    -0.09
    /or
    -0.07
    rell
    -0.07
    øj
    -0.07
    ÑĢÑĥÑĤ
    -0.06
    guard
    -0.06
    ento
    -0.06
    .about
    -0.06
    /her
    -0.06
    POSITIVE LOGITS
    gether
    0.09
    wchar
    0.08
    857
    0.08
    ìĦľ
    0.08
     latter
    0.08
    jourd
    0.07
    ChangedEventArgs
    0.07
    ungan
    0.07
    ERRU
    0.07
    ector
    0.07
    Activations Density 0.010%

    No Known Activations