© 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. 30211
    Prev
    Next
    INDEX
    Explanations

    numerical data and metrics related to growth and performance

    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
    .fromString
    -0.08
    alama
    -0.08
    awan
    -0.07
    ushima
    -0.07
    encent
    -0.07
    eniable
    -0.07
    ulumi
    -0.07
    upert
    -0.07
    _ARG
    -0.07
    imos
    -0.07
    POSITIVE LOGITS
     annually
    0.10
     yearly
    0.10
     annual
    0.09
    ë§Īëĭ¤
    0.08
     Annual
    0.07
     Burl
    0.07
    annual
    0.07
    CTL
    0.07
     every
    0.06
     Mol
    0.06
    Activations Density 0.011%

    No Known Activations