© 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 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. 82833
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" in various 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
     Pie
    -0.07
    aki
    -0.07
    ala
    -0.06
    982
    -0.06
     regards
    -0.06
     pie
    -0.06
    aar
    -0.06
    antage
    -0.05
    inka
    -0.05
     connexion
    -0.05
    POSITIVE LOGITS
    ITHER
    0.08
    assis
    0.07
    _beh
    0.07
    outu
    0.07
    UGE
    0.07
    RECT
    0.07
    witter
    0.07
    asty
    0.07
    tring
    0.07
    غÙĨ
    0.07
    Activations Density 0.029%

    No Known Activations