© 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. 41527
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "has" and its various conjugations to indicate possession and ongoing actions

    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
    ucci
    -0.07
    agma
    -0.07
    itol
    -0.06
    İ·
    -0.06
    lrt
    -0.06
    order
    -0.06
    otic
    -0.06
    ersh
    -0.05
     containment
    -0.05
    locker
    -0.05
    POSITIVE LOGITS
    IDS
    0.06
    cape
    0.06
    راÙĨÛĮ
    0.06
    hem
    0.06
    kur
    0.06
    .Solid
    0.06
    yme
    0.06
     ÙĪص
    0.06
    609
    0.06
     createSelector
    0.06
    Activations Density 0.024%

    No Known Activations