© 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. 17-LLAMASCOPE-RES-131K
    11. 93918
    Prev
    Next
    INDEX
    Explanations

    programming terminology and references related to object-oriented concepts and data management

    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
    ÏĮδ
    -0.07
    uml
    -0.07
    uet
    -0.06
    yms
    -0.06
    agn
    -0.06
     mez
    -0.05
    jedn
    -0.05
    _DECLARE
    -0.05
    amins
    -0.05
    ierre
    -0.05
    POSITIVE LOGITS
    à¥įà¤Ĺत
    0.06
    lien
    0.06
    ekil
    0.06
    .Magenta
    0.06
     inn
    0.06
    ester
    0.06
    nen
    0.06
    lias
    0.06
     Threads
    0.06
    emme
    0.06
    Activations Density 0.314%

    No Known Activations