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. 96082
    Prev
    Next
    INDEX
    Explanations

    occurrences of script or related coding elements in the text

    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
     åĥ
    -0.06
     Thur
    -0.06
    elves
    -0.06
    ooth
    -0.06
    wi
    -0.06
    DAC
    -0.06
    amble
    -0.06
    port
    -0.05
     incoming
    -0.05
    airs
    -0.05
    POSITIVE LOGITS
     seedu
    0.08
    ospel
    0.07
    æģ©
    0.07
     Leben
    0.07
    venir
    0.07
    PECT
    0.07
    detect
    0.07
    isko
    0.07
    pNet
    0.07
    gb
    0.07
    Activations Density 0.001%

    No Known Activations