© 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. 87509
    Prev
    Next
    INDEX
    Explanations

    items and resources related to education and training

    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
    xED
    -0.07
    orda
    -0.07
     Beard
    -0.07
    ÛĮÙĨÚ©
    -0.06
     -*-č↵
    -0.06
    VML
    -0.06
     Credential
    -0.06
     Rahman
    -0.06
     Burl
    -0.06
    noinspection
    -0.06
    POSITIVE LOGITS
     student
    0.07
    itol
    0.07
     students
    0.07
     Student
    0.07
    lish
    0.06
     purchase
    0.06
     uniform
    0.06
     buy
    0.06
     purchases
    0.06
    aghan
    0.06
    Activations Density 0.003%

    No Known Activations