© 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. 15581
    Prev
    Next
    INDEX
    Explanations

    references to touring or travel related to music events

    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
    pector
    -0.07
     Everyday
    -0.07
    units
    -0.07
    abor
    -0.07
    unday
    -0.06
    .terminate
    -0.06
     Eisen
    -0.06
    ê»
    -0.06
     Alo
    -0.06
    ala
    -0.06
    POSITIVE LOGITS
    lick
    0.07
     halls
    0.07
    rapped
    0.07
     globe
    0.07
    mamak
    0.06
    nee
    0.06
    WithDuration
    0.06
    æł¡
    0.06
    _attached
    0.06
     campuses
    0.06
    Activations Density 0.004%

    No Known Activations