© 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. 120742
    Prev
    Next
    INDEX
    Explanations

    instances of the word "nestled" or similar terms that convey a sense of being located in a scenic or cozy setting

    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
    иÑģÑĮ
    -0.07
    airy
    -0.07
    bpp
    -0.07
    agal
    -0.07
    жив
    -0.07
    仲
    -0.07
    edith
    -0.07
    (æ°´
    -0.06
     porr
    -0.06
    pdata
    -0.06
    POSITIVE LOGITS
    neath
    0.07
     behind
    0.07
     away
    0.07
    maid
    0.06
    Ļ
    0.06
     entre
    0.06
    weet
    0.06
     into
    0.06
    -away
    0.06
     between
    0.06
    Activations Density 0.004%

    No Known Activations