© 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. 17-LLAMASCOPE-RES-131K
    11. 3947
    Prev
    Next
    INDEX
    Explanations

    phrases related to homeownership and real estate investment

    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
    osl
    -0.07
    pees
    -0.07
    ê¶ģ
    -0.07
    ois
    -0.06
    ienes
    -0.06
    à¸Ĩ
    -0.06
     Slee
    -0.06
     sy
    -0.06
     Consolid
    -0.06
    pis
    -0.06
    POSITIVE LOGITS
    _esc
    0.06
    utsche
    0.06
    žel
    0.06
    erce
    0.06
    allon
    0.06
    imoto
    0.06
    eah
    0.06
    eka
    0.06
    384
    0.06
    üyük
    0.05
    Activations Density 0.006%

    No Known Activations