© 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. 54186
    Prev
    Next
    INDEX
    Explanations

    instances of configuration or status descriptions in technical contexts

    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
     Ñĩином
    -0.06
    avou
    -0.06
    rypton
    -0.06
    ÅĦ
    -0.06
    Uvs
    -0.06
    оÑıÑĤ
    -0.06
     Pension
    -0.06
    ConverterFactory
    -0.06
    _LCD
    -0.06
     Nixon
    -0.05
    POSITIVE LOGITS
     exist
    0.12
     exists
    0.12
    åŃĺåľ¨
    0.12
     existence
    0.12
     present
    0.12
     presence
    0.10
     vorhand
    0.10
     presente
    0.10
    exists
    0.10
     existed
    0.10
    Activations Density 0.031%

    No Known Activations