© 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. 18401
    Prev
    Next
    INDEX
    Explanations

    actions related to cleaning, food preparation, and maintenance tasks

    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
    ily
    -0.07
     Bour
    -0.06
     Inn
    -0.06
    ules
    -0.06
    enu
    -0.06
    /us
    -0.05
    insky
    -0.05
     Mos
    -0.05
    ux
    -0.05
    R
    -0.05
    POSITIVE LOGITS
    ddf
    0.08
     your
    0.07
    ะà¹ģ
    0.07
    opi
    0.07
    .usermodel
    0.07
    conti
    0.07
    hexdigest
    0.07
    dden
    0.07
    ieren
    0.07
    ưỡng
    0.07
    Activations Density 0.043%

    No Known Activations