© 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 EvalsExportsAPI 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. 29330
    Prev
    Next
    INDEX
    Explanations

    references to hotels and their amenities

    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
    .scalablytyped
    -0.08
    ÅŁk
    -0.07
    кÑĢа
    -0.07
    htub
    -0.07
    á»įt
    -0.07
    кÑĥл
    -0.07
    ÅĻet
    -0.07
    prit
    -0.07
    ÅĻÃŃd
    -0.07
    lique
    -0.07
    POSITIVE LOGITS
     Circular
    0.06
    arse
    0.06
     Gregory
    0.05
    comp
    0.05
    Parcelable
    0.05
    ارÛĮ
    0.05
    åº
    0.05
    nia
    0.05
    _CFG
    0.05
    ero
    0.05
    Activations Density 0.009%

    No Known Activations