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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76273
    Prev
    Next
    INDEX
    Explanations

    elements related to home and property maintenance

    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
    mazon
    -0.09
    ä¿¡ç͍
    -0.07
    stu
    -0.07
    stan
    -0.06
    IED
    -0.06
    -schema
    -0.06
    خاب
    -0.06
    mainwindow
    -0.06
    онÑĮ
    -0.06
    ETCH
    -0.06
    POSITIVE LOGITS
    imoto
    0.07
    inters
    0.06
    Enumerator
    0.06
    imos
    0.06
    oma
    0.06
     tipped
    0.06
    uce
    0.06
    zie
    0.06
    zia
    0.05
    animations
    0.05
    Activations Density 0.001%

    No Known Activations