© 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. 71857
    Prev
    Next
    INDEX
    Explanations

    occurrences of document metadata elements such as descriptions and keywords

    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
    stile
    -0.07
    rana
    -0.07
    cket
    -0.07
    ùa
    -0.07
    cus
    -0.07
    ói
    -0.07
    ullan
    -0.07
    vro
    -0.06
    incinn
    -0.06
    innacle
    -0.06
    POSITIVE LOGITS
    304
    0.07
    ni
    0.06
     Hopkins
    0.06
    Ãĭ
    0.06
    clerosis
    0.06
    uda
    0.06
    eneric
    0.06
    Viewport
    0.06
    decay
    0.06
    ASE
    0.05
    Activations Density 0.001%

    No Known Activations