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. 96055
    Prev
    Next
    INDEX
    Explanations

    references to web browsing and navigation

    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
    ------+
    -0.06
    ér
    -0.06
    lord
    -0.06
    Browse
    -0.06
     crackdown
    -0.06
     (~(
    -0.06
    dbContext
    -0.06
     пÑĢог
    -0.06
    ower
    -0.05
     grinding
    -0.05
    POSITIVE LOGITS
    .SIG
    0.07
    IGHL
    0.07
    /tos
    0.06
    cola
    0.06
    phas
    0.06
    ãĥ¼ãĥį
    0.06
    ãģĤãĤĬãģĮ
    0.06
    ãĥ³ãĥĦ
    0.06
    swick
    0.06
    enville
    0.06
    Activations Density 0.000%

    No Known Activations