© 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. 59431
    Prev
    Next
    INDEX
    Explanations

    content related to waste removal and cleanliness

    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
    posables
    -0.07
    uste
    -0.07
     æŃ
    -0.07
    lyph
    -0.07
    ÃĹ↵↵
    -0.07
    juan
    -0.06
    .mob
    -0.06
     Ost
    -0.06
     ван
    -0.06
    POSITIVE LOGITS
    ch
    0.06
    atham
    0.06
    finder
    0.06
    iva
    0.06
    untas
    0.06
    è¦
    0.06
    ors
    0.06
    pta
    0.06
    -pills
    0.06
    INDER
    0.06
    Activations Density 0.009%

    No Known Activations