© 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. 15141
    Prev
    Next
    INDEX
    Explanations

    references to email communications and newsletters

    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
    utsch
    -0.07
     Hol
    -0.07
    weet
    -0.06
     Uncategorized
    -0.06
    rome
    -0.06
    otta
    -0.06
    -range
    -0.06
    æĸĻ
    -0.05
    ymbols
    -0.05
     ActionTypes
    -0.05
    POSITIVE LOGITS
    Assignable
    0.07
    .Modules
    0.07
    -only
    0.07
    vanished
    0.07
    ÑĢеб
    0.07
    ģını
    0.07
    /print
    0.06
    ROI
    0.06
    ãĥ³ãĥĦ
    0.06
    ASIC
    0.06
    Activations Density 0.004%

    No Known Activations