© 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. 108103
    Prev
    Next
    INDEX
    Explanations

    references to collections or categories, particularly in relation to art or design

    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
    ικα
    -0.08
    bole
    -0.08
    ̧
    -0.07
     STREET
    -0.07
    esis
    -0.07
    atorio
    -0.07
    amar
    -0.07
    -cluster
    -0.07
    à¤ķरण
    -0.07
    icari
    -0.07
    POSITIVE LOGITS
    fully
    0.06
     deep
    0.06
    uchs
    0.06
    REA
    0.06
    Bug
    0.06
    N
    0.05
    unda
    0.05
    website
    0.05
     Campbell
    0.05
     N
    0.05
    Activations Density 0.000%

    No Known Activations