© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 119627
    Prev
    Next
    INDEX
    Explanations

    references to legal professionals and their qualifications in the context of property and bankruptcy

    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
    _readable
    -0.07
    mtx
    -0.06
     attractiveness
    -0.06
    ankind
    -0.06
    ering
    -0.06
     ras
    -0.06
    леж
    -0.06
     left
    -0.06
    ely
    -0.06
    iem
    -0.06
    POSITIVE LOGITS
     specialization
    0.10
     spécial
    0.09
     specialize
    0.09
     specializing
    0.08
     ÑģпеÑĨÑĸ
    0.08
     specialized
    0.08
     specializes
    0.08
    special
    0.08
     poss
    0.08
     expertise
    0.08
    Activations Density 0.018%

    No Known Activations