© 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. 17-LLAMASCOPE-RES-131K
    11. 29007
    Prev
    Next
    INDEX
    Explanations

    phrases related to convenience and time-saving in daily activities

    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
    lop
    -0.07
    иÑĩа
    -0.07
     ballo
    -0.06
    apo
    -0.06
     entreg
    -0.06
    gı
    -0.06
    оÑģÑĤаÑĤ
    -0.06
    jte
    -0.06
    оÑģÑĤÑĥп
    -0.06
    phin
    -0.06
    POSITIVE LOGITS
     travel
    0.09
     driving
    0.08
     traveling
    0.08
     traffic
    0.08
    travel
    0.07
    ulos
    0.07
     travelling
    0.07
     transportation
    0.07
    elize
    0.07
     Driving
    0.07
    Activations Density 0.021%

    No Known Activations