© 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. 54650
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods or approaches

    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
    afone
    -0.07
    ëŀĢ
    -0.07
    CCC
    -0.07
    uels
    -0.07
    uhl
    -0.07
    ÑĩÑĥк
    -0.07
    pagen
    -0.07
    ideon
    -0.07
    rlen
    -0.07
     اÙĦÙĤد
    -0.07
    POSITIVE LOGITS
    0.07
    vari
    0.06
     ticket
    0.06
     route
    0.06
    evi
    0.05
    дав
    0.05
    subpackage
    0.05
    ched
    0.05
    473
    0.05
    andle
    0.05
    Activations Density 0.007%

    No Known Activations