© 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. 54360
    Prev
    Next
    INDEX
    Explanations

    phrases related to entertainment events and reviews

    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
    ниÑĨÑı
    -0.07
     IHttp
    -0.07
    cript
    -0.07
    opi
    -0.07
    ovit
    -0.06
    agem
    -0.06
    éľį
    -0.06
    stor
    -0.06
    hap
    -0.06
    éŁ¿
    -0.06
    POSITIVE LOGITS
     Unsigned
    0.09
    unsigned
    0.07
     unsigned
    0.07
    Unsigned
    0.07
     artists
    0.07
    artists
    0.07
    Frameworks
    0.07
     festival
    0.06
     cover
    0.06
    _Device
    0.06
    Activations Density 0.038%

    No Known Activations