© 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. 74023
    Prev
    Next
    INDEX
    Explanations

    verbs that convey a sense of reporting, stating, or describing observations

    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
    ød
    -0.07
    bay
    -0.07
    akk
    -0.07
    ников
    -0.07
    lev
    -0.07
    linger
    -0.07
    iran
    -0.07
     ----------------------------------------------------------------------↵
    -0.07
    опÑĢи
    -0.06
    огда
    -0.06
    POSITIVE LOGITS
    ingly
    0.07
    ively
    0.07
     Sirius
    0.07
    antwort
    0.06
    ÙĪØ°
    0.06
    phas
    0.06
    ãĥ«ãĥī
    0.06
    äch
    0.06
    icone
    0.06
    celik
    0.06
    Activations Density 0.013%

    No Known Activations