© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61314
    Prev
    Next
    INDEX
    Explanations

    references to astronomical bodies and their characteristics

    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
    _variant
    -0.07
    GuidId
    -0.07
    opies
    -0.07
    éĴĪ
    -0.07
    åde
    -0.07
    ughter
    -0.07
    .EntityManager
    -0.07
    pagen
    -0.06
    okrat
    -0.06
     localVar
    -0.06
    POSITIVE LOGITS
     Bing
    0.07
     myth
    0.06
     mutable
    0.06
    ucken
    0.06
     cooling
    0.06
    _fact
    0.06
    ames
    0.06
     immutable
    0.06
     car
    0.06
     Pointer
    0.06
    Activations Density 0.003%

    No Known Activations