© 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. 2001
    Prev
    Next
    INDEX
    Explanations

    mentions of specifications and related technical terms

    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
     Deng
    -0.07
    ule
    -0.06
    ì²´
    -0.06
    emer
    -0.06
    atty
    -0.06
    Äįet
    -0.06
    eral
    -0.06
    PLICATE
    -0.06
    missive
    -0.06
    yor
    -0.05
    POSITIVE LOGITS
    اÙĪÙĨد
    0.08
    icamente
    0.07
    .GPIO
    0.07
    izr
    0.07
    QS
    0.07
    enties
    0.07
    DSA
    0.07
     autos
    0.06
    897
    0.06
    infeld
    0.06
    Activations Density 0.001%

    No Known Activations