© 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. 105668
    Prev
    Next
    INDEX
    Explanations

    terms related to Bayesian statistical analysis

    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
     polov
    -0.07
    ãģ¤ãģ¶
    -0.07
     beaut
    -0.07
     Grat
    -0.07
    _KERNEL
    -0.07
     strand
    -0.07
    olib
    -0.06
    utos
    -0.06
    powers
    -0.06
    bedo
    -0.06
    POSITIVE LOGITS
    rzy
    0.07
    agento
    0.07
    orias
    0.07
     Reform
    0.06
     marginal
    0.06
    idUser
    0.06
     lou
    0.06
     Sadd
    0.06
    chner
    0.06
    опÑĢи
    0.06
    Activations Density 0.028%

    No Known Activations