© 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. 9-LLAMASCOPE-RES-131K
    11. 95288
    Prev
    Next
    INDEX
    Explanations

    negations or qualifiers in statements

    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
    ovable
    -0.07
    ght
    -0.06
    utsche
    -0.06
    lah
    -0.06
    ElementsByTagName
    -0.06
    Tween
    -0.06
     VÅ¡ech
    -0.06
    id
    -0.06
    bose
    -0.06
    ewed
    -0.06
    POSITIVE LOGITS
    ãĥ©ãĥĥãĤ¯
    0.07
    æħ§
    0.07
    IVER
    0.07
    ì°¸
    0.07
    ÑĢана
    0.06
    акон
    0.06
    879
    0.06
    _decorator
    0.06
     ÐļÑĢа
    0.06
    à¥įयवस
    0.06
    Activations Density 0.048%

    No Known Activations