© 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. 62484
    Prev
    Next
    INDEX
    Explanations

    citations or references in a scholarly context

    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
    alan
    -0.07
    ÑĢиÑĤи
    -0.06
    atics
    -0.06
    oe
    -0.06
    terminal
    -0.06
    voÅĻ
    -0.06
     sink
    -0.06
    xt
    -0.06
    lick
    -0.06
    atik
    -0.06
    POSITIVE LOGITS
    ennen
    0.07
    roring
    0.06
    erras
    0.06
    gewater
    0.06
    ENTA
    0.06
    zsche
    0.06
    SharedPointer
    0.06
    ispens
    0.06
     Ke
    0.06
     Combo
    0.06
    Activations Density 0.016%

    No Known Activations