© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 27565
    Prev
    Next
    INDEX
    Explanations

    terms related to habitation and inhabitants

    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
    orie
    -0.07
     ReSharper
    -0.07
    ASM
    -0.07
    asmus
    -0.07
    enia
    -0.07
    /xhtml
    -0.07
    orias
    -0.07
    feito
    -0.07
    ASE
    -0.07
    ennie
    -0.07
    POSITIVE LOGITS
    oreal
    0.07
    ta
    0.06
    oreach
    0.06
    uar
    0.06
    ings
    0.06
    itals
    0.06
     dwell
    0.06
    lust
    0.06
    ry
    0.06
     -*-č↵
    0.06
    Activations Density 0.008%

    No Known Activations