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. 22-LLAMASCOPE-RES-131K
    6. 5367
    Prev
    Next
    INDEX
    Explanations

    references to satellite data and NASA

    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
    ิà¸ķย
    -0.07
    ¶Į
    -0.07
    pell
    -0.07
    θμ
    -0.07
    izza
    -0.07
     Ders
    -0.07
    éĨ´
    -0.07
    .dtd
    -0.07
    EMPLARY
    -0.07
    emm
    -0.07
    POSITIVE LOGITS
    VO
    0.06
    .wrap
    0.06
    tty
    0.06
     unhealthy
    0.06
    енз
    0.06
    :len
    0.05
    .utility
    0.05
     позд
    0.05
    æİĽ
    0.05
     Mane
    0.05
    Activations Density 0.001%

    No Known Activations