© 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 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. 118712
    Prev
    Next
    INDEX
    Explanations

    URLs and domain names related to websites

    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
    rosso
    -0.08
    abis
    -0.07
    _Tis
    -0.07
    ideo
    -0.07
    ÑĢож
    -0.07
    ungan
    -0.07
    èº
    -0.07
     bilder
    -0.07
    _mE
    -0.07
    iska
    -0.07
    POSITIVE LOGITS
    /how
    0.06
     how
    0.06
    /
    0.06
     ser
    0.06
     top
    0.06
    iel
    0.06
     Erd
    0.06
     cre
    0.05
    :
    0.05
     elsewhere
    0.05
    Activations Density 0.008%

    No Known Activations