© 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. 9-LLAMASCOPE-RES-131K
    11. 98587
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to methods and systems used in various processes, particularly in hiring and learning

    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
    ucha
    -0.08
    ÑĥÑģÑĤи
    -0.07
    lü
    -0.06
    enden
    -0.06
    TypeEnum
    -0.06
    atham
    -0.06
    riba
    -0.06
    TypeInfo
    -0.06
    hle
    -0.06
    imits
    -0.06
    POSITIVE LOGITS
    alone
    0.07
    aeda
    0.07
    ental
    0.07
    LOC
    0.06
    apr
    0.06
    jac
    0.06
    .openg
    0.06
    abstract
    0.06
    ceae
    0.06
    aca
    0.06
    Activations Density 0.039%

    No Known Activations