© 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 EvalsExportsinterp-engineNEWAPI 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. 104345
    Prev
    Next
    INDEX
    Explanations

    occurrences of the variable 'v'

    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
    opus
    -0.08
     NDEBUG
    -0.07
    лем
    -0.07
    c
    -0.06
    .getvalue
    -0.06
    orphic
    -0.06
    cio
    -0.06
    é¹
    -0.06
    _QMARK
    -0.06
    arah
    -0.06
    POSITIVE LOGITS
     sal
    0.07
     Cir
    0.06
    kees
    0.06
    ênh
    0.06
    niž
    0.06
    utas
    0.06
     âĸij
    0.06
     cir
    0.06
     car
    0.06
     quan
    0.06
    Activations Density 0.000%

    No Known Activations