© 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. 15902
    Prev
    Next
    INDEX
    Explanations

    references to growth or escalation, particularly in context of quantitative increases

    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
    REFERRED
    -0.07
    ãģĬãĤĬ
    -0.07
    (tol
    -0.07
    ÙĤÙĬ
    -0.06
    fit
    -0.06
    resentation
    -0.06
    shape
    -0.06
    ืà¸Ńà¸Ķ
    -0.06
    smith
    -0.06
    ว
    -0.06
    POSITIVE LOGITS
    /de
    0.13
     likelihood
    0.08
    /remove
    0.07
    htar
    0.07
    Å¡lo
    0.07
     chances
    0.07
    hof
    0.07
    imals
    0.07
    ased
    0.07
     amount
    0.07
    Activations Density 0.043%

    No Known Activations