© 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. 54574
    Prev
    Next
    INDEX
    Explanations

    concepts related to persuasive techniques

    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
     wishlist
    -0.06
    æľĭ
    -0.06
    stras
    -0.06
    /files
    -0.06
     wage
    -0.06
    maybe
    -0.06
    abal
    -0.05
    Record
    -0.05
     Wishlist
    -0.05
     thing
    -0.05
    POSITIVE LOGITS
     audiences
    0.07
    ãĥ³ãĥĦ
    0.07
     yours
    0.07
    amo
    0.07
     story
    0.07
     circulating
    0.07
     your
    0.07
    bidden
    0.06
     %+
    0.06
    ÑĴ
    0.06
    Activations Density 0.002%

    No Known Activations