© 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. 58193
    Prev
    Next
    INDEX
    Explanations

    numerical references, like dates or statistics

    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
    ardin
    -0.07
    親
    -0.07
    okud
    -0.07
    ãģķãĤī
    -0.06
    _calibration
    -0.06
    ardu
    -0.06
    عا
    -0.06
    наÑĤ
    -0.06
    ÙĪÙĦات
    -0.06
    ajes
    -0.06
    POSITIVE LOGITS
    isci
    0.08
    upp
    0.07
    itre
    0.07
    echa
    0.06
    inci
    0.06
    ãĥ©ãĤ¯
    0.06
    éo
    0.06
    ikal
    0.06
     Adler
    0.06
    contres
    0.06
    Activations Density 0.002%

    No Known Activations