© 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. 76456
    Prev
    Next
    INDEX
    Explanations

    references to processes or conditions related to environmental impacts and sustainability

    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
    ét
    -0.06
     manifest
    -0.06
     fisse
    -0.06
     urge
    -0.06
    baz
    -0.06
    à¥Įर
    -0.06
    -el
    -0.06
    ove
    -0.06
    ég
    -0.06
    572
    -0.06
    POSITIVE LOGITS
    ByPrimaryKey
    0.07
    burgh
    0.07
    uti
    0.07
     addCriterion
    0.06
    ç§ij
    0.06
    /tiny
    0.06
    eren
    0.06
    icom
    0.06
    /inet
    0.06
    utos
    0.06
    Activations Density 0.000%

    No Known Activations