© 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. 60984
    Prev
    Next
    INDEX
    Explanations

    pronouns and their associated actions 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
    ãİ
    -0.07
    -UA
    -0.07
    rror
    -0.06
    /legal
    -0.06
    ERM
    -0.06
    ermo
    -0.06
    stu
    -0.06
    leen
    -0.06
     ãĢ
    -0.06
    LOB
    -0.06
    POSITIVE LOGITS
    /or
    0.09
     subsequently
    0.08
     consequently
    0.07
     therefore
    0.07
    ique
    0.07
     consequ
    0.07
     thereafter
    0.07
    /OR
    0.07
    thus
    0.07
    eza
    0.07
    Activations Density 0.033%

    No Known Activations