© 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. 118749
    Prev
    Next
    INDEX
    Explanations

    expressions related to participation and involvement in various 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
     pornos
    -0.10
    âĪı
    -0.09
    abwe
    -0.09
     огÑĢа
    -0.09
    ůl
    -0.09
    галÑĸ
    -0.09
    _contrib
    -0.09
    erus
    -0.09
    vise
    -0.08
    erva
    -0.08
    POSITIVE LOGITS
    id
    0.07
     oneself
    0.06
    and
    0.06
    ment
    0.06
    SD
    0.06
    1
    0.06
    aling
    0.06
    f
    0.06
    illing
    0.06
    itude
    0.06
    Activations Density 0.127%

    No Known Activations