© 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. 81133
    Prev
    Next
    INDEX
    Explanations

    phrases that express invitation or permission

    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
    arkin
    -0.07
    ané
    -0.06
     trú
    -0.06
    imens
    -0.06
    (æ°´
    -0.06
    idores
    -0.06
    ụy
    -0.06
    озвÑĢаÑī
    -0.06
    (æľ¨
    -0.06
    an
    -0.06
    POSITIVE LOGITS
    undos
    0.07
    021
    0.07
     McD
    0.06
    ovky
    0.06
    γι
    0.06
    und
    0.06
    缤
    0.06
    821
    0.06
    ross
    0.06
    ances
    0.06
    Activations Density 0.005%

    No Known Activations