© 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. 4833
    Prev
    Next
    INDEX
    Explanations

    references to the names of journals and listings in real estate

    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
    esta
    -0.08
    croft
    -0.07
    aca
    -0.07
    omba
    -0.07
    anan
    -0.07
    esel
    -0.07
    chner
    -0.07
    mutable
    -0.07
    wahl
    -0.06
    á»ĭ
    -0.06
    POSITIVE LOGITS
    rops
    0.06
    bands
    0.06
    EI
    0.06
    æľºæŀĦ
    0.06
    003
    0.06
     Bout
    0.06
    variables
    0.06
     Becker
    0.06
    bins
    0.05
    elik
    0.05
    Activations Density 0.011%

    No Known Activations