© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56352
    Prev
    Next
    INDEX
    Explanations

    elements related to photography and camera techniques

    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
    ладÑĥ
    -0.07
    nez
    -0.07
    _subplot
    -0.07
    cente
    -0.06
     Gad
    -0.06
    isVisible
    -0.06
    é¾Ħ
    -0.06
    ÙģراÙĨ
    -0.06
     PROPERTY
    -0.06
     Visible
    -0.06
    POSITIVE LOGITS
    cri
    0.07
    usc
    0.07
    chimp
    0.06
     Hand
    0.06
     walk
    0.06
    olson
    0.06
     portraits
    0.06
    ê°IJ
    0.06
    模å¼ı
    0.06
     subjects
    0.06
    Activations Density 0.011%

    No Known Activations