© 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. 9-LLAMASCOPE-RES-131K
    11. 97360
    Prev
    Next
    INDEX
    Explanations

    numerical data related to passenger statistics in transportation

    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
    âĢ¦↵↵↵
    -0.07
    thag
    -0.07
    chant
    -0.07
    ayah
    -0.07
    UED
    -0.07
     AssertionError
    -0.07
    eneg
    -0.07
    enders
    -0.06
    æijĩ
    -0.06
    night
    -0.06
    POSITIVE LOGITS
     ga
    0.06
     sÃłn
    0.06
    lac
    0.06
    ạch
    0.06
     Lazar
    0.06
    Charset
    0.06
     hop
    0.06
    opia
    0.06
     Ald
    0.06
     Jur
    0.06
    Activations Density 0.011%

    No Known Activations