© 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. 75056
    Prev
    Next
    INDEX
    Explanations

    terms related to cleaning and removing unwanted substances

    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
    梨
    -0.07
    ertas
    -0.06
    ouver
    -0.06
    ambre
    -0.06
    535
    -0.06
    halb
    -0.06
    ventus
    -0.06
    illez
    -0.06
     r
    -0.06
    ë°±
    -0.06
    POSITIVE LOGITS
     stubborn
    0.07
     traces
    0.07
    ầm
    0.06
    èīĩ
    0.06
     pig
    0.06
     Stub
    0.06
    ánu
    0.06
     dirt
    0.06
     âĢ»
    0.06
     deposits
    0.06
    Activations Density 0.009%

    No Known Activations