© 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 EvalsExportsAPI 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. 77296
    Prev
    Next
    INDEX
    Explanations

    references to poverty and its implications

    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
    ccione
    -0.09
    ordinate
    -0.07
     liberation
    -0.06
    ieres
    -0.06
    TECTED
    -0.06
    缮åīį
    -0.06
     currently
    -0.06
     opposite
    -0.06
    etz
    -0.06
    arto
    -0.06
    POSITIVE LOGITS
     minimalist
    0.06
    Æ°á»Ŀng
    0.06
    ndef
    0.06
    IDDEN
    0.06
     spas
    0.06
    æ¸IJ
    0.06
     Enum
    0.06
     Evel
    0.06
     cen
    0.06
    poÄį
    0.06
    Activations Density 0.000%

    No Known Activations