© 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. 127416
    Prev
    Next
    INDEX
    Explanations

    references to weighting and averaging in statistical models

    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
    ếu
    -0.07
    aucoup
    -0.07
    зÑĥ
    -0.07
    iras
    -0.07
     sor
    -0.06
     norge
    -0.06
    azard
    -0.06
    ERSHEY
    -0.06
    ког
    -0.06
    å¤ĩ
    -0.06
    POSITIVE LOGITS
     weight
    0.14
     weighting
    0.13
     weights
    0.12
    weight
    0.12
     Weight
    0.12
     WEIGHT
    0.11
    -weight
    0.11
    .weight
    0.10
     weighted
    0.10
    Weight
    0.10
    Activations Density 0.032%

    No Known Activations