© 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. 57296
    Prev
    Next
    INDEX
    Explanations

    phrases related to community impact and corporate responsibility

    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
    زÙħ
    -0.08
     Ø´Ùĩ
    -0.07
    ằ
    -0.07
    ARSE
    -0.07
    .Interop
    -0.07
     smr
    -0.07
    gebn
    -0.07
     vidéos
    -0.07
    åĿĤ
    -0.07
    _CONVERT
    -0.07
    POSITIVE LOGITS
     ours
    0.06
    ena
    0.06
    ourd
    0.06
     our
    0.06
    formats
    0.06
     Foam
    0.06
     Xxx
    0.06
     xxx
    0.06
     XXX
    0.05
    .legend
    0.05
    Activations Density 0.001%

    No Known Activations