© 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. 9-LLAMASCOPE-RES-131K
    11. 96575
    Prev
    Next
    INDEX
    Explanations

    numerical data related to awards or recognition

    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
    agara
    -0.08
    rint
    -0.08
    483
    -0.07
    ätt
    -0.07
    áv
    -0.07
    jian
    -0.07
    alone
    -0.06
    itra
    -0.06
    tog
    -0.06
    ellas
    -0.06
    POSITIVE LOGITS
    @nate
    0.07
    using
    0.07
    _tF
    0.07
    _tA
    0.06
    _mB
    0.06
    _mD
    0.06
     Highlights
    0.06
     "&#
    0.06
    _mC
    0.06
    OfWork
    0.06
    Activations Density 0.008%

    No Known Activations