© 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. 54789
    Prev
    Next
    INDEX
    Explanations

    verb forms of "to be" indicating states of existence or conditions

    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
    azz
    -0.06
    illing
    -0.06
    c
    -0.06
    jong
    -0.06
    aux
    -0.06
     Ge
    -0.06
    ARS
    -0.06
    ale
    -0.06
    old
    -0.06
    kos
    -0.06
    POSITIVE LOGITS
    ëľ
    0.08
    ?=.*
    0.08
    typeid
    0.08
    uther
    0.07
     resil
    0.07
    ãĥ¶
    0.07
    Concurrency
    0.07
    iveau
    0.07
    /GPL
    0.07
    ắc
    0.07
    Activations Density 0.008%

    No Known Activations