© 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. 81997
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "to be" in various contexts

    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
    rente
    -0.08
    hod
    -0.07
    ARAM
    -0.07
    alama
    -0.06
     Dy
    -0.06
    reece
    -0.06
    ouver
    -0.06
    ymph
    -0.06
    cd
    -0.06
    illez
    -0.06
    POSITIVE LOGITS
     know
    0.07
    -know
    0.07
    åѦä¼ļ
    0.06
     be
    0.06
     обÑıзаÑĤелÑĮно
    0.06
    cher
    0.06
    avi
    0.06
    563
    0.06
    @param
    0.06
    lein
    0.06
    Activations Density 0.030%

    No Known Activations