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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58330
    Prev
    Next
    INDEX
    Explanations

    phrases indicating no obligations or costs associated with a service

    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
    ÄŁÃ¼
    -0.08
    ilin
    -0.07
    oug
    -0.07
    aits
    -0.07
    á»ĩn
    -0.07
    een
    -0.07
     hon
    -0.07
    δια
    -0.06
    ITED
    -0.06
    ilos
    -0.06
    POSITIVE LOGITS
     obligation
    0.09
     pressure
    0.08
     commitment
    0.08
     pressured
    0.08
     Pressure
    0.07
    pressure
    0.07
    Pressure
    0.07
     pressures
    0.06
     Obl
    0.06
     obligations
    0.06
    Activations Density 0.003%

    No Known Activations