© 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. 87012
    Prev
    Next
    INDEX
    Explanations

    negative statements or references to problems and concerns

    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
    ãģŁãģĹ
    -0.07
    Ãłng
    -0.07
    á»įc
    -0.07
    kus
    -0.07
    Capabilities
    -0.06
    izar
    -0.06
     ì¦Ŀ
    -0.06
     Appro
    -0.06
     Disco
    -0.06
     sogar
    -0.06
    POSITIVE LOGITS
     nor
    0.10
     neither
    0.10
     nÃło
    0.08
     any
    0.07
     specific
    0.07
     žádné
    0.07
     anymore
    0.07
     ningún
    0.07
    nor
    0.07
    Neither
    0.07
    Activations Density 0.017%

    No Known Activations