© 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. 108254
    Prev
    Next
    INDEX
    Explanations

    phrases related to expertise, authority, and community involvement

    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
    bjerg
    -0.07
    emme
    -0.07
    ارÙĩ
    -0.06
    637
    -0.06
    ULO
    -0.06
    ÅĻ
    -0.06
    otu
    -0.06
    628
    -0.06
    lednÃŃ
    -0.06
    ä½³
    -0.06
    POSITIVE LOGITS
     Bowman
    0.07
    charm
    0.06
    ìĦŃ
    0.06
    ĤŃ
    0.06
     Lock
    0.06
    opl
    0.06
    uiltin
    0.06
     forwards
    0.06
     Eigen
    0.06
     lock
    0.06
    Activations Density 0.000%

    No Known Activations