© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 88056
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that express alternatives or choices

    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
     Bilim
    -0.07
    ãĤ¦ãĥĪ
    -0.07
    etc
    -0.07
    weetalert
    -0.07
    392
    -0.07
    709
    -0.07
    ucer
    -0.07
    pls
    -0.06
    ystick
    -0.06
    /etc
    -0.06
    POSITIVE LOGITS
    bane
    0.08
     quarter
    0.06
     ç¦
    0.06
    acular
    0.06
    amento
    0.06
    lund
    0.06
     Quarter
    0.06
     pit
    0.06
    rese
    0.06
    amon
    0.06
    Activations Density 0.001%

    No Known Activations