© 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 EvalsExportsinterp-engineNEWAPI 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. 95660
    Prev
    Next
    INDEX
    Explanations

    expressions of assistance or service-related promises

    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
    象
    -0.07
    attering
    -0.07
    _OC
    -0.07
    ạ
    -0.06
    оÑĢож
    -0.06
    -urlencoded
    -0.06
    oders
    -0.06
     Reminder
    -0.06
    .GetText
    -0.06
     ÙĪا
    -0.06
    POSITIVE LOGITS
    asca
    0.07
     reply
    0.07
     bir
    0.06
     answers
    0.06
     hang
    0.06
     opp
    0.06
     div
    0.06
     answer
    0.06
     wherever
    0.06
     whatever
    0.06
    Activations Density 0.010%

    No Known Activations