© 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. 104921
    Prev
    Next
    INDEX
    Explanations

    corporate entities and their associations in financial contexts

    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
    aras
    -0.08
    ouz
    -0.07
    .fm
    -0.07
    ılıç
    -0.07
    ResourceId
    -0.07
    DBObject
    -0.07
    errated
    -0.07
    eview
    -0.07
     Uz
    -0.07
    seealso
    -0.07
    POSITIVE LOGITS
    asic
    0.08
    /-
    0.06
    cale
    0.06
    ERSIST
    0.05
    iron
    0.05
    whose
    0.05
     whose
    0.05
    undle
    0.05
    /OR
    0.05
    /Foundation
    0.05
    Activations Density 0.010%

    No Known Activations