© 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. 15-LLAMASCOPE-RES-131K
    11. 27405
    Prev
    Next
    INDEX
    Explanations

    references to children or related concepts

    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
     impl
    -0.07
    ady
    -0.07
     seg
    -0.07
    lik
    -0.07
    allo
    -0.07
    ây
    -0.06
    abay
    -0.06
    aram
    -0.06
     super
    -0.06
    ::.
    -0.06
    POSITIVE LOGITS
    (assert
    0.07
    ãĤħ
    0.07
    Subtitle
    0.07
    xon
    0.07
    InputModule
    0.07
     dioxide
    0.07
    apgolly
    0.06
    inous
    0.06
    _iff
    0.06
    еÑĢом
    0.06
    Activations Density 0.001%

    No Known Activations