© 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. 82636
    Prev
    Next
    INDEX
    Explanations

    code structure elements, particularly the syntax related to class definitions and public access

    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
    ợ
    -0.07
     Marin
    -0.07
    rak
    -0.06
    rung
    -0.06
    件
    -0.06
    bee
    -0.06
     içi
    -0.06
     Khan
    -0.06
    onta
    -0.06
    év
    -0.06
    POSITIVE LOGITS
    Howard
    0.07
    _exempt
    0.07
    977
    0.06
    abus
    0.06
     Westbrook
    0.06
     Rig
    0.06
    £
    0.06
     Howard
    0.06
    leground
    0.06
    uang
    0.06
    Activations Density 0.001%

    No Known Activations