© 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. 94670
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the structure or sequence of parts

    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
    ä¸Ģ人
    -0.08
    erva
    -0.07
     ngược
    -0.07
    DisplayStyle
    -0.07
    á»ij
    -0.07
    .Bot
    -0.06
    ins
    -0.06
    Ñĸб
    -0.06
    èo
    -0.06
    kan
    -0.06
    POSITIVE LOGITS
     this
    0.06
     our
    0.06
    usan
    0.06
    pill
    0.06
    usi
    0.06
    nings
    0.06
     Associates
    0.06
    this
    0.06
    sys
    0.06
    andum
    0.06
    Activations Density 0.011%

    No Known Activations