© 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. 56082
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual growth and transformation

    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
     Brut
    -0.07
    墨
    -0.07
    _Statics
    -0.07
    ensa
    -0.07
    ANGE
    -0.07
    åŃĺåľ¨
    -0.07
    çŃĴ
    -0.06
    omid
    -0.06
    _Parms
    -0.06
     vur
    -0.06
    POSITIVE LOGITS
     peace
    0.07
    adows
    0.06
     Alle
    0.06
    Æ¡m
    0.06
     access
    0.06
    jiang
    0.06
    Alle
    0.06
    fé
    0.06
    ñana
    0.06
     rem
    0.05
    Activations Density 0.036%

    No Known Activations