© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84859
    Prev
    Next
    INDEX
    Explanations

    mentions of features or capabilities of devices or products

    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
    isser
    -0.08
    ÙĩÙĨ
    -0.07
    orda
    -0.07
     Malone
    -0.07
    raki
    -0.07
    å´İ
    -0.07
     ActionTypes
    -0.07
    łģ
    -0.07
    VOID
    -0.07
    acet
    -0.07
    POSITIVE LOGITS
     features
    0.10
    features
    0.09
    /features
    0.09
     Features
    0.08
     feature
    0.08
     such
    0.08
     FEATURES
    0.08
    such
    0.07
    (features
    0.07
    eatures
    0.06
    Activations Density 0.021%

    No Known Activations