© 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. 82338
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to flexibility and options in plans or arrangements

    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
    óÅĤ
    -0.08
    anges
    -0.07
    iddles
    -0.07
     (~
    -0.07
    hev
    -0.07
    ddy
    -0.06
    inch
    -0.06
    ãģ«ãģĬ
    -0.06
    ille
    -0.06
    getDrawable
    -0.06
    POSITIVE LOGITS
     gonna
    0.07
    gon
    0.07
    æĪIJ人
    0.06
     comprom
    0.06
    lix
    0.06
    veis
    0.06
    ?↵
    0.06
    acle
    0.06
     Ã¶ÄŁret
    0.06
    ạn
    0.05
    Activations Density 0.003%

    No Known Activations