© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105142
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to software functionalities and applications

    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
     station
    -0.06
    emouth
    -0.06
     tinder
    -0.06
    ETF
    -0.06
     fingerprint
    -0.06
     cord
    -0.06
     Cord
    -0.06
     Station
    -0.06
     Agency
    -0.05
     Palest
    -0.05
    POSITIVE LOGITS
    riba
    0.09
    okie
    0.07
    arehouse
    0.07
    Views
    0.07
    imers
    0.07
    ÑĢÑĮ
    0.07
    erp
    0.07
     ERP
    0.07
    .precision
    0.07
     Quote
    0.07
    Activations Density 0.013%

    No Known Activations