© 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. 28601
    Prev
    Next
    INDEX
    Explanations

    elements related to metadata and categorization of documents

    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
    elpers
    -0.07
    smouth
    -0.06
    vg
    -0.06
    emouth
    -0.06
    ibur
    -0.06
    çķ
    -0.06
     Hairst
    -0.06
     paramName
    -0.06
    arend
    -0.06
    asher
    -0.06
    POSITIVE LOGITS
    agine
    0.09
    +:
    0.07
    alytics
    0.06
    :
    0.06
    oÅĪ
    0.06
    CTS
    0.06
    uD
    0.06
    lein
    0.06
    askan
    0.06
    CSR
    0.06
    Activations Density 0.014%

    No Known Activations