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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-LLAMASCOPE-RES-131K
    6. 96086
    Prev
    Next
    INDEX
    Explanations

    phrases related to effectiveness and methods of prevention

    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
    roid
    -0.06
    atron
    -0.06
    ucher
    -0.06
    iners
    -0.06
    uro
    -0.06
    IDL
    -0.06
    ugo
    -0.06
     bottled
    -0.06
    usalem
    -0.05
     wire
    -0.05
    POSITIVE LOGITS
    ستÛĮ
    0.07
    aeda
    0.07
     smr
    0.07
    овеÑĢ
    0.07
    ExecutionContext
    0.07
     ÙĦÙĦت
    0.07
     дÑĢÑĥж
    0.06
    ometr
    0.06
    ãi
    0.06
     Halk
    0.06
    Activations Density 0.022%

    No Known Activations