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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88674
    Prev
    Next
    INDEX
    Explanations

    phrases pertaining to uniqueness and social structures

    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
    -0.07
    ÑĨенÑĤÑĢа
    -0.06
     nab
    -0.06
     odak
    -0.06
    _predicate
    -0.06
    ensa
    -0.06
    &M
    -0.06
     nues
    -0.06
    lemn
    -0.06
     zdrav
    -0.06
    POSITIVE LOGITS
    opr
    0.07
    -transitional
    0.07
    usan
    0.06
    ä¼¼
    0.06
    IDGET
    0.06
    orable
    0.06
    ãĥį
    0.06
    ocate
    0.06
    åİŁæĿ¥
    0.06
     Wind
    0.06
    Activations Density 0.005%

    No Known Activations