© 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. 88262
    Prev
    Next
    INDEX
    Explanations

    terms related to waste management and dumpster rental

    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
    olate
    -0.07
    BUM
    -0.07
    (SP
    -0.07
    ,},↵
    -0.07
    AZY
    -0.06
    blick
    -0.06
    åIJ¹
    -0.06
     zbo
    -0.06
    ulist
    -0.06
    zi
    -0.06
    POSITIVE LOGITS
    igon
    0.07
    eon
    0.07
    rade
    0.07
    èĵ
    0.07
    ä¹ī
    0.06
    MatrixMode
    0.06
    arat
    0.06
    eny
    0.06
    conciliation
    0.06
    onymous
    0.06
    Activations Density 0.007%

    No Known Activations