© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27235
    Prev
    Next
    INDEX
    Explanations

    terms related to property status and occupancy

    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
    undry
    -0.07
    awan
    -0.07
    á»ĵng
    -0.07
    ifique
    -0.06
    ury
    -0.06
    andon
    -0.06
    357
    -0.06
    spÄĽ
    -0.06
    ادÛĮ
    -0.06
     IReadOnly
    -0.06
    POSITIVE LOGITS
    criptor
    0.06
    _PLUGIN
    0.06
    515
    0.06
     dolu
    0.06
    551
    0.06
     Plugin
    0.06
    uyá»ħn
    0.06
     FG
    0.06
     Beet
    0.06
     Miller
    0.06
    Activations Density 0.000%

    No Known Activations