© 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. 288
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or expressions of intent

    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
    eka
    -0.07
     MV
    -0.06
    åĪ°åºķ
    -0.06
    élé
    -0.06
     wil
    -0.06
    igor
    -0.06
    conte
    -0.06
     will
    -0.06
    robat
    -0.06
     Might
    -0.06
    POSITIVE LOGITS
     varsa
    0.07
    _PLL
    0.07
    sd
    0.07
    ادات
    0.07
    _Api
    0.06
    ostat
    0.06
     prefer
    0.06
    igr
    0.06
    456
    0.06
    853
    0.06
    Activations Density 0.004%

    No Known Activations