© 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 EvalsExportsinterp-engineNEWAPI 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. 72791
    Prev
    Next
    INDEX
    Explanations

    discussions about online platforms and their privacy policies

    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
    iphy
    -0.06
    completion
    -0.06
    à¸ŀล
    -0.06
    оÑĩно
    -0.06
    lah
    -0.06
    elon
    -0.06
    -ser
    -0.06
     hy
    -0.06
     mill
    -0.06
    exam
    -0.06
    POSITIVE LOGITS
     today
    0.07
    ACHINE
    0.06
     evangel
    0.06
    odie
    0.06
    odd
    0.06
     tonight
    0.06
    iad
    0.06
     URLRequest
    0.05
    today
    0.05
    cz
    0.05
    Activations Density 0.027%

    No Known Activations