© 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. 73100
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "the" and related function words

    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
    ãĥ¼ãĥ
    -0.08
    pesan
    -0.07
     naken
    -0.06
    ÙĥÙĬÙĬÙģ
    -0.06
    .Emit
    -0.06
    anio
    -0.06
    amik
    -0.06
    út
    -0.06
     Clifford
    -0.06
    rava
    -0.06
    POSITIVE LOGITS
    fad
    0.06
    iron
    0.06
     commissions
    0.06
    _TOOLTIP
    0.06
    IRON
    0.06
    mamak
    0.06
     Ùĩذا
    0.06
    MLS
    0.06
    OKIE
    0.06
    ugas
    0.06
    Activations Density 0.347%

    No Known Activations