© 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. 18265
    Prev
    Next
    INDEX
    Explanations

    mentions of the city Boulder in various contexts

    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
    downloads
    -0.08
    nell
    -0.08
    nel
    -0.07
    elijk
    -0.07
    VOKE
    -0.07
    loys
    -0.07
    ned
    -0.07
    sah
    -0.07
    ãģ
    -0.07
    eh
    -0.07
    POSITIVE LOGITS
    icious
    0.08
    sb
    0.07
    stone
    0.06
    achs
    0.06
    tron
    0.06
    oku
    0.06
    hower
    0.06
    led
    0.06
    inox
    0.06
    leared
    0.06
    Activations Density 0.003%

    No Known Activations