Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44090
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of writing systems and their characteristics

    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
    ITLE
    -0.09
    зÑı
    -0.07
    екаÑĢ
    -0.07
    Ïģιά
    -0.07
    ATAR
    -0.07
    ISTIC
    -0.07
    INA
    -0.07
     koc
    -0.07
     Helena
    -0.07
    ÑģÑĤÑĢа
    -0.06
    POSITIVE LOGITS
    ique
    0.24
    iques
    0.21
    iquement
    0.16
    IQUE
    0.16
    rique
    0.14
    qi
    0.13
    igue
    0.12
    érique
    0.12
    iquer
    0.12
    lique
    0.12
    Activations Density 0.015%

    No Known Activations