© 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. 95614
    Prev
    Next
    INDEX
    Explanations

    concepts related to family and caregiving in the context of mental health

    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
    ongs
    -0.09
    adiens
    -0.07
    urally
    -0.07
    ñana
    -0.07
     íij¸
    -0.07
    flt
    -0.07
     settled
    -0.06
    ilters
    -0.06
    ìĦ±ìĿ´
    -0.06
    ç»ĻæĪij
    -0.06
    POSITIVE LOGITS
     family
    0.06
     involvement
    0.06
    hoc
    0.06
     liver
    0.06
     collateral
    0.05
    lh
    0.05
     paraph
    0.05
    oen
    0.05
    isci
    0.05
     thi
    0.05
    Activations Density 0.003%

    No Known Activations