© 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. 15375
    Prev
    Next
    INDEX
    Explanations

    verbs related to existence and occurrence 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
    aroo
    -0.06
    виÑĩай
    -0.06
    decltype
    -0.06
    entine
    -0.06
    rina
    -0.06
    ting
    -0.06
    ---</
    -0.06
    /lists
    -0.06
    qrst
    -0.05
    vrd
    -0.05
    POSITIVE LOGITS
     olan
    0.07
    õi
    0.07
    oque
    0.06
    lad
    0.06
    entlich
    0.06
     Portrait
    0.06
     olursa
    0.06
     ÙĪاÙĦتÙĬ
    0.06
    clar
    0.06
    OSP
    0.06
    Activations Density 0.043%

    No Known Activations