© 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. 88640
    Prev
    Next
    INDEX
    Explanations

    elements related to graphical rendering and parameters in programming 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
     latter
    -0.11
    actly
    -0.07
    serrat
    -0.07
    GetInstance
    -0.07
    tement
    -0.07
    รà¸ĩ
    -0.07
    ведиÑĤе
    -0.07
    amedi
    -0.07
    izzo
    -0.06
    ãģ¡ãĤī
    -0.06
    POSITIVE LOGITS
    odore
    0.06
    adays
    0.06
    oretical
    0.06
    west
    0.06
    kových
    0.06
    _PROFILE
    0.06
    _transient
    0.06
    urge
    0.06
    /#
    0.05
    ripper
    0.05
    Activations Density 0.099%

    No Known Activations