© 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. 104155
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a desire for visualizing or anticipating outcomes

    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
    uste
    -0.08
    å¾ĴæŃ©
    -0.07
    illon
    -0.07
    ileceÄŁini
    -0.07
    und
    -0.07
    urs
    -0.06
    _DLL
    -0.06
    ï¸ı
    -0.06
    Äį
    -0.06
    awan
    -0.06
    POSITIVE LOGITS
    QWidget
    0.07
    iqueta
    0.07
    lea
    0.07
    apus
    0.07
    avia
    0.07
     someone
    0.06
     chá»ĭ
    0.06
     Rot
    0.06
     vocab
    0.06
     firsthand
    0.06
    Activations Density 0.015%

    No Known Activations