© 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 EvalsExportsAPI 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. 87282
    Prev
    Next
    INDEX
    Explanations

    words related to earth or land forms, especially variations of "terra" and related terms

    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
     Spears
    -0.07
    etty
    -0.07
    cket
    -0.07
    elor
    -0.07
    ocker
    -0.07
    ivamente
    -0.07
    urgeon
    -0.06
    .Suppress
    -0.06
    oref
    -0.06
    ieval
    -0.06
    POSITIVE LOGITS
    forming
    0.07
    anean
    0.07
    icone
    0.07
    achat
    0.07
     firma
    0.07
     terr
    0.06
    loh
    0.06
    ikler
    0.06
    ugg
    0.06
    orm
    0.06
    Activations Density 0.017%

    No Known Activations