© 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. 106591
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one"

    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
    rosse
    -0.08
    ffi
    -0.07
    inois
    -0.07
    aney
    -0.07
    roid
    -0.06
    IBC
    -0.06
    anca
    -0.06
    chten
    -0.06
    ruk
    -0.06
    pery
    -0.06
    POSITIVE LOGITS
     of
    0.08
    cle
    0.07
     among
    0.06
    ixture
    0.06
     Kew
    0.06
    woke
    0.06
     Cad
    0.06
    among
    0.05
     Zu
    0.05
     favorite
    0.05
    Activations Density 0.013%

    No Known Activations