© 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. 70106
    Prev
    Next
    INDEX
    Explanations

    actions and states related to care and nurturing

    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
    eling
    -0.07
    oba
    -0.07
    ulp
    -0.07
    uko
    -0.07
    ona
    -0.07
    akt
    -0.07
    ccess
    -0.07
    лага
    -0.07
    bject
    -0.06
    aces
    -0.06
    POSITIVE LOGITS
     themselves
    0.10
     oneself
    0.10
     yourself
    0.09
     siÄĻ
    0.09
     herself
    0.09
     ourselves
    0.09
     myself
    0.09
    èĩªå·±
    0.08
     himself
    0.08
     thems
    0.07
    Activations Density 0.046%

    No Known Activations