© 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. 126700
    Prev
    Next
    INDEX
    Explanations

    references to music albums and singles

    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
    òi
    -0.07
    sites
    -0.06
    éal
    -0.06
    isson
    -0.06
     Meyer
    -0.06
    Ñīик
    -0.06
    éĤ
    -0.06
    utenberg
    -0.06
    icast
    -0.06
    Compiled
    -0.06
    POSITIVE LOGITS
     American
    0.09
     american
    0.09
    American
    0.09
    -American
    0.07
    .setParameter
    0.07
    .Bounds
    0.07
    ipp
    0.06
    krom
    0.06
    owi
    0.06
    ĵn
    0.06
    Activations Density 0.011%

    No Known Activations