© 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. 56738
    Prev
    Next
    INDEX
    Explanations

    URLs and parameters related to medical content

    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
    ingu
    -0.07
     Papers
    -0.07
    ÑĥÑĪ
    -0.06
    _guard
    -0.06
    guard
    -0.06
    á»ı
    -0.05
    lung
    -0.05
    umont
    -0.05
    íı°
    -0.05
    ahir
    -0.05
    POSITIVE LOGITS
    سط
    0.08
    æħ
    0.08
    ạn
    0.07
    chapter
    0.07
    /gin
    0.07
    bic
    0.07
    ritz
    0.07
    aises
    0.07
    isbn
    0.07
     Chapter
    0.07
    Activations Density 0.001%

    No Known Activations