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. 43860
    Prev
    Next
    INDEX
    Explanations

    numerical information related to events and organizations

    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
    rych
    -0.07
    ковий
    -0.06
    esis
    -0.06
    shortcut
    -0.06
    ÙĴÙĩ
    -0.06
    _days
    -0.06
    emplates
    -0.06
    icia
    -0.06
    аÑĤо
    -0.06
    ož
    -0.06
    POSITIVE LOGITS
     annual
    0.30
     Annual
    0.25
    annual
    0.24
     yearly
    0.23
    Annual
    0.23
     ann
    0.21
     annually
    0.20
     bi
    0.19
    _ann
    0.18
    ann
    0.17
    Activations Density 0.033%

    No Known Activations