© 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. 40416
    Prev
    Next
    INDEX
    Explanations

    information related to waste management services

    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
    uros
    -0.08
    apon
    -0.07
    yh
    -0.07
    indow
    -0.06
    973
    -0.06
    allas
    -0.06
    559
    -0.06
    emap
    -0.06
    fusc
    -0.06
    cores
    -0.06
    POSITIVE LOGITS
    istra
    0.08
    elt
    0.07
     Pent
    0.06
    ileceÄŁi
    0.06
    nuts
    0.06
    orda
    0.06
    ãĤµãĤ¤
    0.06
    WEEN
    0.06
    gett
    0.06
     Hed
    0.06
    Activations Density 0.004%

    No Known Activations