© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106731
    Prev
    Next
    INDEX
    Explanations

    concepts related to spirituality and the relationship between the divine and human experience

    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
    eka
    -0.07
    reh
    -0.07
    ifo
    -0.06
    hta
    -0.06
    earable
    -0.06
    coni
    -0.06
     timelines
    -0.06
     dow
    -0.06
    IQ
    -0.06
    enu
    -0.06
    POSITIVE LOGITS
     itself
    0.10
    Tester
    0.06
    ADIO
    0.06
    ανά
    0.06
    uyo
    0.06
    .Butter
    0.06
    =:
    0.06
    enha
    0.06
    SizeMode
    0.06
    elage
    0.06
    Activations Density 0.092%

    No Known Activations