© 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. 17-LLAMASCOPE-RES-131K
    11. 93439
    Prev
    Next
    INDEX
    Explanations

    phrases related to aspirations and finding a personalized home

    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
    ouch
    -0.07
    Å¡ov
    -0.06
    ủng
    -0.06
    ppe
    -0.06
    sed
    -0.06
     ($.
    -0.06
    ertools
    -0.06
    Ø®Ùħ
    -0.06
    еÑģи
    -0.06
    à¹Ģà¸ľ
    -0.06
    POSITIVE LOGITS
     home
    0.11
     house
    0.09
     dream
    0.09
     lifestyle
    0.08
    家
    0.08
     living
    0.08
    home
    0.07
    dream
    0.07
    dech
    0.07
    /Dk
    0.07
    Activations Density 0.019%

    No Known Activations