© 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. 28668
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and database operations

    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
    æ²ĸ
    -0.08
    nict
    -0.07
    andır
    -0.07
     CONSEQUENTIAL
    -0.07
    odal
    -0.07
    BindingUtil
    -0.07
    newInstance
    -0.07
    ilib
    -0.07
    ัà¸ĩส
    -0.06
    оиÑĤ
    -0.06
    POSITIVE LOGITS
     state
    0.07
    .dispatch
    0.07
     State
    0.07
    estone
    0.06
    state
    0.06
    avel
    0.06
    acia
    0.06
     side
    0.06
    State
    0.06
     Flame
    0.06
    Activations Density 0.004%

    No Known Activations