© 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. 91953
    Prev
    Next
    INDEX
    Explanations

    references to "cover" in various contexts, particularly related to music or protective measures

    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
    zon
    -0.08
    bons
    -0.07
    zelf
    -0.07
    eger
    -0.07
    uras
    -0.07
    ALLY
    -0.07
    scri
    -0.06
    sons
    -0.06
    angi
    -0.06
    maal
    -0.06
    POSITIVE LOGITS
    ings
    0.11
    alls
    0.10
    ages
    0.08
    gence
    0.07
    neath
    0.07
    age
    0.07
    dale
    0.07
    posit
    0.07
    eds
    0.07
    .sponge
    0.06
    Activations Density 0.029%

    No Known Activations