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. 44300
    Prev
    Next
    INDEX
    Explanations

    the presence of HTML tags and coding syntax

    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
    ÑĢеÑĤ
    -0.06
    rement
    -0.06
    oret
    -0.06
    .codes
    -0.06
    readcrumb
    -0.06
     synonym
    -0.06
    ission
    -0.05
     ÄIJá»ĭnh
    -0.05
    éĮ¯
    -0.05
    -pic
    -0.05
    POSITIVE LOGITS
    =edge
    0.07
    8
    0.07
    11
    0.07
     crossorigin
    0.07
    10
    0.07
    7
    0.07
    iete
    0.06
    6
    0.06
     template
    0.06
    Stick
    0.06
    Activations Density 0.003%

    No Known Activations