© 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. 75532
    Prev
    Next
    INDEX
    Explanations

    procedures related to plant care and protection

    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
     -
    -0.07
    cloud
    -0.06
     –
    -0.06
    871
    -0.06
     —
    -0.06
     --
    -0.06
     trú
    -0.06
    902
    -0.06
    llen
    -0.06
    å±ķ
    -0.06
    POSITIVE LOGITS
    onec
    0.07
    ROTO
    0.07
    .scalablytyped
    0.07
    ycastle
    0.07
     ÐľÑĥ
    0.06
    ebilecek
    0.06
    ê·Ģ
    0.06
    hek
    0.06
    ocz
    0.06
    gow
    0.06
    Activations Density 0.001%

    No Known Activations