© 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. 81965
    Prev
    Next
    INDEX
    Explanations

    phrases indicating family relationships and revelations

    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
     æķħ
    -0.07
    cdecl
    -0.07
    zia
    -0.07
    /Instruction
    -0.07
    Ä±ÅŁÄ±k
    -0.06
     irres
    -0.06
    ÑĤоÑİ
    -0.06
    /backend
    -0.06
    ä¼ı
    -0.06
    оÑĢÑĤÑĥ
    -0.06
    POSITIVE LOGITS
     nos
    0.08
     notice
    0.07
     sno
    0.07
     demand
    0.07
     demanded
    0.07
     suspicious
    0.07
    Susp
    0.07
     detection
    0.06
     discovery
    0.06
    azzi
    0.06
    Activations Density 0.030%

    No Known Activations