© 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. 125601
    Prev
    Next
    INDEX
    Explanations

    words associated with tranquility and peace

    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
    маз
    -0.08
    kla
    -0.07
    ngr
    -0.07
    á»ĩ
    -0.07
    BED
    -0.07
    ibu
    -0.07
    culate
    -0.07
    bach
    -0.07
    ACHE
    -0.07
    živ
    -0.07
    POSITIVE LOGITS
    ude
    0.08
    etti
    0.07
    umb
    0.07
    illis
    0.07
    illy
    0.07
    oto
    0.06
    um
    0.06
     Chest
    0.06
     Sheldon
    0.06
    å°Ħ
    0.06
    Activations Density 0.002%

    No Known Activations