© 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. 58449
    Prev
    Next
    INDEX
    Explanations

    expressions indicating choice or alternatives

    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
     kvin
    -0.07
    eo
    -0.07
    heed
    -0.07
    alte
    -0.06
    ounty
    -0.06
    .singleton
    -0.06
    aylor
    -0.06
    amedi
    -0.06
    uesta
    -0.06
    otropic
    -0.06
    POSITIVE LOGITS
    soever
    0.09
    anged
    0.07
     ones
    0.06
    inking
    0.06
    ampo
    0.06
     DIE
    0.06
    APPLE
    0.06
    theless
    0.06
    ows
    0.06
    åĢī
    0.06
    Activations Density 0.001%

    No Known Activations