© 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. 15-LLAMASCOPE-RES-131K
    6. 551
    Prev
    Next
    INDEX
    Explanations

    keywords related to regulatory or governing contexts

    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
    e
    -0.06
    ifest
    -0.06
    y
    -0.06
    preced
    -0.06
    eper
    -0.06
     EntityType
    -0.05
    raj
    -0.05
    اÛĮد
    -0.05
     thereby
    -0.05
     //================================================================
    -0.05
    POSITIVE LOGITS
    æŀľ
    0.08
    WEEN
    0.07
     RuntimeObject
    0.07
    Æ°á»Ľ
    0.07
    TRA
    0.07
    iger
    0.07
    egra
    0.07
    ilik
    0.07
    Vtbl
    0.07
    omu
    0.07
    Activations Density 0.016%

    No Known Activations