© 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. 56225
    Prev
    Next
    INDEX
    Explanations

    geographic locations or place names

    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
    acker
    -0.07
    dez
    -0.06
    osy
    -0.06
     Terrace
    -0.06
    compass
    -0.06
     kür
    -0.06
    dz
    -0.06
    wrong
    -0.05
    angkan
    -0.05
    icer
    -0.05
    POSITIVE LOGITS
    ÃĹ↵↵
    0.09
    Scalars
    0.07
    ูà¸Ĭ
    0.07
    ibur
    0.07
     uydu
    0.07
    olynomial
    0.07
    onica
    0.07
    ÙĪارÙĩ
    0.07
    ãĥĸãĥŃ
    0.07
    íĥķ
    0.07
    Activations Density 0.030%

    No Known Activations