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

    Neuronpedia

    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. 129791
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to dimensions and geometry

    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
    ncy
    -0.07
    oke
    -0.07
    ÑĦек
    -0.07
    agine
    -0.06
    bourg
    -0.06
     Erotic
    -0.06
     رÙĪاÙĨ
    -0.06
    vice
    -0.06
     arrog
    -0.06
     Slave
    -0.06
    POSITIVE LOGITS
    (PHP
    0.07
    athers
    0.07
    gart
    0.07
    örü
    0.06
    arella
    0.06
    438
    0.06
     sums
    0.06
    ulace
    0.06
    ufs
    0.06
     Mess
    0.06
    Activations Density 0.050%

    No Known Activations