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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76511
    Prev
    Next
    INDEX
    Explanations

    references to object properties and methods in a programming context

    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
    odom
    -0.07
     ãħĩãħĩ
    -0.07
    <<<
    -0.07
     weather
    -0.07
    #ab
    -0.06
    weather
    -0.06
    å½
    -0.06
    decess
    -0.06
     ÐļÑĢи
    -0.06
     Yao
    -0.06
    POSITIVE LOGITS
    anine
    0.07
    atonin
    0.07
    smarty
    0.06
    munition
    0.06
    aterial
    0.06
    å±ĭ
    0.06
    itori
    0.06
    ancell
    0.06
    furt
    0.06
    andro
    0.06
    Activations Density 0.026%

    No Known Activations