© 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. 95386
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to children's activities and experiences

    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
    ãĥ³ãĤº
    -0.07
    ãĥĥãĥģ
    -0.07
     paran
    -0.07
    ÑģÑĮк
    -0.07
     eldre
    -0.07
     slip
    -0.06
    getti
    -0.06
    à¹Ģà¸ĭà¸Ńร
    -0.06
    readcr
    -0.06
    arez
    -0.06
    POSITIVE LOGITS
     interest
    0.08
     Interest
    0.07
    eya
    0.07
    interest
    0.07
    Interest
    0.07
    -interest
    0.07
    lÃŃn
    0.06
    geh
    0.06
    zs
    0.06
     boys
    0.06
    Activations Density 0.020%

    No Known Activations