© 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. 17-LLAMASCOPE-RES-131K
    11. 71760
    Prev
    Next
    INDEX
    Explanations

    references to grease and related concepts

    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
    zial
    -0.07
    主人
    -0.07
    Smarty
    -0.07
    êt
    -0.06
    ksen
    -0.06
    éĨ´
    -0.06
    antan
    -0.06
    ardy
    -0.06
    lain
    -0.06
    umeric
    -0.06
    POSITIVE LOGITS
    iness
    0.08
    /o
    0.07
    yp
    0.07
     grub
    0.06
    رÙĪت
    0.06
    bum
    0.06
    works
    0.06
    514
    0.06
    hound
    0.06
     harb
    0.06
    Activations Density 0.003%

    No Known Activations