© 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. 39574
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to team selection and recruitment processes

    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
     civilian
    -0.07
     zav
    -0.07
    éŁ¿
    -0.06
    हल
    -0.06
    ivre
    -0.06
     offsetof
    -0.06
    atÃŃm
    -0.06
    _escape
    -0.06
    conversion
    -0.06
     ÙħØ«
    -0.06
    POSITIVE LOGITS
     formed
    0.07
    ewing
    0.06
    cratch
    0.06
     excess
    0.06
     driv
    0.06
    rello
    0.06
    -formed
    0.06
     handful
    0.06
    uts
    0.06
    utures
    0.06
    Activations Density 0.002%

    No Known Activations