© 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. 4512
    Prev
    Next
    INDEX
    Explanations

    patterns of numeric codes or identifiers related to various products and methods

    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
     prim
    -0.07
     Raven
    -0.06
    709
    -0.06
    ment
    -0.06
    onom
    -0.06
     rule
    -0.06
     profess
    -0.06
     rud
    -0.05
     Gh
    -0.05
    ool
    -0.05
    POSITIVE LOGITS
    uitka
    0.08
    ongsTo
    0.08
    ché
    0.08
    ĨĴ
    0.08
    .scalablytyped
    0.08
    senal
    0.07
    raquo
    0.07
    ÎŃλ
    0.07
    PLIC
    0.07
    itele
    0.07
    Activations Density 0.020%

    No Known Activations