© 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. 38774
    Prev
    Next
    INDEX
    Explanations

    actions related to gardening and plant care

    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
    á»ī
    -0.09
    linger
    -0.08
    ób
    -0.08
    enan
    -0.07
    asics
    -0.07
     chatte
    -0.07
    ÑĥÑĤи
    -0.07
     zbo
    -0.07
     вк
    -0.07
    åĪ»
    -0.07
    POSITIVE LOGITS
     flush
    0.07
     growth
    0.07
     Growth
    0.07
     struct
    0.07
     limb
    0.06
     performed
    0.06
    zie
    0.06
     Cutting
    0.06
     cut
    0.06
     limbs
    0.06
    Activations Density 0.003%

    No Known Activations