© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 128250
    Prev
    Next
    INDEX
    Explanations

    terms related to minerals and mining processes

    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
    enza
    -0.06
     sophistication
    -0.06
    #+
    -0.06
    tridge
    -0.06
     metals
    -0.06
    avic
    -0.06
    uilder
    -0.06
    itchen
    -0.06
    enas
    -0.06
    umen
    -0.06
    POSITIVE LOGITS
    Ľå»º
    0.07
    bff
    0.07
    ServiceImpl
    0.07
    bserv
    0.07
     عÙħÙĦÙĬØ©
    0.07
    .jms
    0.06
    гал
    0.06
    Scripts
    0.06
     Tal
    0.06
     huyết
    0.06
    Activations Density 0.005%

    No Known Activations