© 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. 5486
    Prev
    Next
    INDEX
    Explanations

    instances of content posting and engagement metrics

    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
    ithe
    -0.07
    _registered
    -0.06
    ropri
    -0.06
    .Xaml
    -0.06
    otton
    -0.06
     ven
    -0.06
    THR
    -0.06
    лик
    -0.06
    Ñĸг
    -0.06
    legen
    -0.06
    POSITIVE LOGITS
    elper
    0.07
    azio
    0.07
    ksi
    0.06
    quina
    0.06
    zos
    0.06
    uez
    0.06
    167
    0.06
    andard
    0.06
    ories
    0.06
    267
    0.06
    Activations Density 0.001%

    No Known Activations