© 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. 69617
    Prev
    Next
    INDEX
    Explanations

    specific durations of time or measurements

    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
     addCriterion
    -0.08
    å³
    -0.07
    loon
    -0.07
    ÃŃÅĻ
    -0.07
    frei
    -0.07
    gewater
    -0.07
    insky
    -0.06
    tero
    -0.06
    è
    -0.06
    otal
    -0.06
    POSITIVE LOGITS
    âm
    0.06
     PM
    0.05
     Pf
    0.05
     Agenda
    0.05
     tent
    0.05
    ÑĢовиÑĩ
    0.05
     Pub
    0.05
    raph
    0.05
     âĢı
    0.05
    und
    0.05
    Activations Density 0.009%

    No Known Activations