© 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. 4586
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and relevant biological terminology

    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
    ázd
    -0.07
    DAQ
    -0.07
    avage
    -0.06
    _UNS
    -0.06
    SWG
    -0.06
    isoft
    -0.06
    alling
    -0.06
    astle
    -0.06
    èĭ¦
    -0.06
     postcode
    -0.06
    POSITIVE LOGITS
     Pik
    0.07
    .atom
    0.07
    426
    0.07
     eng
    0.06
    rray
    0.06
     AUTHORS
    0.06
     PED
    0.06
    eyi
    0.06
    eref
    0.06
     letter
    0.06
    Activations Density 0.013%

    No Known Activations