© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96376
    Prev
    Next
    INDEX
    Explanations

    prominent television show titles and characters

    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
     KromÄĽ
    -0.08
    ICODE
    -0.08
    iggins
    -0.07
    ä»Ķ
    -0.07
    ÑĢÑĸм
    -0.07
    onso
    -0.07
    utura
    -0.07
    onz
    -0.07
    igung
    -0.07
    езд
    -0.07
    POSITIVE LOGITS
    &R
    0.07
    unch
    0.06
    arts
    0.06
     Gra
    0.06
    lock
    0.06
    123
    0.06
     Tou
    0.06
     fem
    0.06
    ordered
    0.05
    kn
    0.05
    Activations Density 0.003%

    No Known Activations