© 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. 17-LLAMASCOPE-RES-131K
    11. 129903
    Prev
    Next
    INDEX
    Explanations

    web domains and associated database references

    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
    аÑĢа
    -0.07
    formance
    -0.07
    omat
    -0.06
    istar
    -0.06
    ÐĿÐĨ
    -0.06
    áv
    -0.06
    ropy
    -0.06
    _firestore
    -0.06
     Hers
    -0.06
    áp
    -0.06
    POSITIVE LOGITS
     {{{
    0.07
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.06
    locks
    0.06
    -stack
    0.06
     Bott
    0.06
     âĢı
    0.06
     urlencode
    0.06
     ,(
    0.06
    женнÑı
    0.06
     portal
    0.06
    Activations Density 0.004%

    No Known Activations