© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96679
    Prev
    Next
    INDEX
    Explanations

    references to a sense of belonging or comfort in a location or environment

    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
    uel
    -0.07
    pare
    -0.06
    жи
    -0.06
    reading
    -0.06
     vn
    -0.06
     tá
    -0.06
    æݧ
    -0.06
    PCP
    -0.06
    ardin
    -0.06
    ÙĨا
    -0.06
    POSITIVE LOGITS
    TEGER
    0.06
    leck
    0.06
    etty
    0.06
     дело
    0.06
     proverb
    0.06
    oly
    0.06
    /il
    0.06
     Wolff
    0.06
    aidu
    0.06
    ahir
    0.06
    Activations Density 0.003%

    No Known Activations