© 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. 87528
    Prev
    Next
    INDEX
    Explanations

    expressions of personal needs or desires

    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
    um
    -0.07
    cl
    -0.06
     amour
    -0.06
    ứng
    -0.06
    iers
    -0.06
    reff
    -0.06
    ApiController
    -0.06
     suff
    -0.06
    ruh
    -0.06
    od
    -0.06
    POSITIVE LOGITS
     Ballard
    0.08
    Interpolator
    0.07
    SEQUENTIAL
    0.07
    aset
    0.07
    zego
    0.07
    ilver
    0.06
    از
    0.06
    æ¢ģ
    0.06
    師
    0.06
    awan
    0.06
    Activations Density 0.003%

    No Known Activations