© 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. 73290
    Prev
    Next
    INDEX
    Explanations

    mentions of content management systems and web publishing platforms

    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
    alten
    -0.07
    indow
    -0.07
    hiba
    -0.07
    ittest
    -0.06
    emed
    -0.06
    ector
    -0.06
    imits
    -0.06
    é¾
    -0.06
    anding
    -0.06
    estre
    -0.06
    POSITIVE LOGITS
     rhyme
    0.07
    simd
    0.06
    PLIC
    0.06
    .imag
    0.06
     rh
    0.06
    ;text
    0.06
    /reference
    0.06
    788
    0.05
     reb
    0.05
    PHPUnit
    0.05
    Activations Density 0.002%

    No Known Activations