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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 79163
    Prev
    Next
    INDEX
    Explanations

    language related to health-related actions, conditions, and assessments

    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
    .AutoComplete
    -0.07
    каж
    -0.07
     zwar
    -0.07
     Yours
    -0.07
    naissance
    -0.06
    .synthetic
    -0.06
    ocol
    -0.06
     ÙĨÙħÙĪØ¯Ùĩ
    -0.06
    øy
    -0.06
     Semi
    -0.06
    POSITIVE LOGITS
    zzle
    0.07
    vester
    0.07
    #
    0.06
    .ย
    0.06
    UGH
    0.06
     McDon
    0.06
    blogs
    0.06
    sr
    0.06
    bew
    0.06
    USTOM
    0.06
    Activations Density 0.041%

    No Known Activations