© 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. 72441
    Prev
    Next
    INDEX
    Explanations

    key terms related to legality and responsibility 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
    ä¸ĬäºĨ
    -0.07
    åIJĦç§į
    -0.07
    obe
    -0.07
    both
    -0.07
     BOTH
    -0.07
     McCart
    -0.07
    phere
    -0.07
    ade
    -0.06
    á»įc
    -0.06
     Both
    -0.06
    POSITIVE LOGITS
     nor
    0.20
    nor
    0.14
     unless
    0.14
    unless
    0.12
     unlike
    0.12
     Nor
    0.11
    Nor
    0.11
     neither
    0.10
     except
    0.10
    Unless
    0.10
    Activations Density 0.037%

    No Known Activations