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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94020
    Prev
    Next
    INDEX
    Explanations

    complex mathematical and programming expressions involving variables and operators

    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
    FileSync
    -0.07
    ptron
    -0.07
    Ãłu
    -0.07
     keÅŁ
    -0.07
    ORB
    -0.07
    kp
    -0.07
    erif
    -0.07
     нада
    -0.07
    OLE
    -0.07
    á»ĵng
    -0.07
    POSITIVE LOGITS
    سÙĪب
    0.06
     Schn
    0.06
    Ì
    0.06
     +
    0.06
    ÃĨ
    0.05
     Trad
    0.05
    andr
    0.05
    Úĺ
    0.05
     Kad
    0.05
    uction
    0.05
    Activations Density 0.058%

    No Known Activations