© 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. 121196
    Prev
    Next
    INDEX
    Explanations

    elements related to ambient sound or noise

    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
    AAF
    -0.08
    fully
    -0.08
    antage
    -0.08
    s
    -0.08
    .scalablytyped
    -0.08
    ses
    -0.07
    anko
    -0.07
    одо
    -0.07
    psilon
    -0.07
    fulness
    -0.07
    POSITIVE LOGITS
    ly
    0.08
    ary
    0.07
    ascus
    0.07
    atic
    0.07
    eting
    0.07
    ÅĤu
    0.07
    iation
    0.07
    PCI
    0.07
    /out
    0.07
    ciler
    0.07
    Activations Density 0.004%

    No Known Activations