© 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. 58947
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" in various contexts

    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
     homosex
    -0.06
    exas
    -0.06
    ulf
    -0.06
    alk
    -0.06
    een
    -0.06
    riter
    -0.06
    Ñģко
    -0.06
     å¨
    -0.06
    xious
    -0.06
    .eu
    -0.06
    POSITIVE LOGITS
     tagged
    0.09
     Uncategorized
    0.07
     Rudd
    0.06
    Unc
    0.06
    âĨIJ
    0.06
    nů
    0.06
    ngör
    0.06
    _CONSOLE
    0.06
    妮
    0.06
    ModelError
    0.06
    Activations Density 0.003%

    No Known Activations