© 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. 41000
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS elements in the document

    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
    ysl
    -0.06
     Leonard
    -0.06
    ikan
    -0.06
    ész
    -0.05
     toString
    -0.05
    ç
    -0.05
    .='
    -0.05
    pole
    -0.05
    zo
    -0.05
    118
    -0.05
    POSITIVE LOGITS
    Äįel
    0.08
     Ñįлек
    0.07
    inyin
    0.07
    åĿĬ
    0.07
    oldem
    0.07
    inux
    0.07
    ocu
    0.07
    aÅŁ
    0.07
    ży
    0.06
    yun
    0.06
    Activations Density 0.001%

    No Known Activations