© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 5102
    Prev
    Next
    INDEX
    Explanations

    the preposition "of."

    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
    ump
    -0.07
    _utilities
    -0.06
    act
    -0.06
    iked
    -0.06
    els
    -0.06
     Warn
    -0.06
     DEFINE
    -0.05
    net
    -0.05
    elles
    -0.05
    umer
    -0.05
    POSITIVE LOGITS
     which
    0.10
    which
    0.09
     коÑĤоÑĢой
    0.08
    roys
    0.08
     коÑĤоÑĢÑĭÑħ
    0.07
     które
    0.07
    #ac
    0.07
    tery
    0.07
    Mahon
    0.07
     οÏĢο
    0.07
    Activations Density 0.003%

    No Known Activations