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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 95993
    Prev
    Next
    INDEX
    Explanations

    references to students in their final year of high school or college

    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
    ÃŃÅ¡
    -0.07
    doctrine
    -0.07
    /language
    -0.06
    lags
    -0.06
    croft
    -0.06
     Consort
    -0.06
    Checksum
    -0.06
    tractive
    -0.06
    -react
    -0.06
     Patron
    -0.06
    POSITIVE LOGITS
    223
    0.06
    otions
    0.06
    گرد
    0.06
    venta
    0.06
    arious
    0.06
    ìĿ´ìŀIJ
    0.06
    .lift
    0.06
    347
    0.05
    ÙĪØ¹
    0.05
    utomation
    0.05
    Activations Density 0.009%

    No Known Activations